obsessive compulsive disorder name pieces
A neuronOne of thousands of tiny dials inside each layer. It reads the text so far and produces a number, its activation, that nudges what the model writes next. in layerOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. 8 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featuredA neuron picked for the full treatment: steering outputs and a written explanation. About 3,000 of the 86,000 neurons are featured., so it has steering outputs.
What this neuron does
This neuron fires on the middle words of mental health and nerve condition names, most often 'Obsessive Compulsive' and 'Tourette'. It also fires on some commas and author names in reference lists. Turning it up did not produce any clear theme in the writing.
Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).
Fires most on
The text windows where this neuron's activationThe number a neuron produces for a token. Large positive means it fired hard; negative means it pushed the other way. was highest. Amber marks positive activation; the outlined tokenA piece of text the model reads at once: often a word, sometimes part of a word or a punctuation mark. is the peak. Hover a token for its strength.
-
forests from southern Honduras south to central Panama. Males sing from small leks at the edge of the forest during the breeding season.⏎Kistler, Ethan, and Thomas S. Schulenberg. 2013. Snowcap (
-
and young adulthood, though they can occur in anyone, of any gender, at any age.”⏎Eating disorders often occur alongside other mental health disorders such as obsessive compulsive disorder, mood disorders, or substance abuse issues. There are several different types
-
M., Chan, K. S.-C., Chan, D. W.-O., & Chung, K. K.-H. (2014, July). Effectiveness of a tiered intervention model in Chinese: A growth model
-
the Singapore River and Kallang Basin in 10 years’ time. The Kallang Basin was<|endoftext|>Symptoms of depression, anxiety, and obsessive compulsive disorders have emerged or worsened for many during the pandemic. This is no
-
on more days than not in the last six months: restlessness, fatigue, irritability, muscle tension, difficulty sleeping and difficulty concentrating.⏎Obsessive Compulsive Disorder (OCD)⏎Obs<|endoftext|>A mobile phone user outside a mobile payment facility
-
processing speed.⏎However, many observations of anxious kids suggest that the symptoms of anxiety could exacerbate slow processing speed. For example, children with Obsessive Compulsive Disorder might appear to complete work slowly because they have developed internal rules such as needing
SteeringAdding a push along a neuron while the model writes, to see how its output changes. Turning it up or down.
Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.
Here is something I have been thinking about lately: "The following: " " A: " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " " "
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
94⏎Reference Count: N/A⏎Hand in Hand. Skills Activities for Tutors and Students.⏎Biles, James J.; And Others⏎The guide is the second in a two-volume series designed to
-
.” Simiolus: Netherlands Quarterly for the History of Art 13.1 (1983): 4–43.⏎Wood, Christopher S. Albrecht Altdorfer and the Origins of Landscape. Chicago:
-
197.⏎Kwong-loi Shun (1997). Mencius and Early Chinese Thought. Stanford University Press.⏎Zhang Pengwei, Guo Qiyong & Wang Bei (2008). New
-
and threatening tone in which many of them were publicly carried forward. For this, both Democrats and Republicans have a share of the blame.⏎Kennan, George F. "The GOP Won the Cold War? Ridiculous." New York
Connections
Show on mapWhich neuronsOne of thousands of tiny dials inside each layer. It reads the text so far and produces a number, its activation, that nudges what the model writes next. in earlier layersOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.
Fed by earlier layers
- L5:66 weakly excites
- L0:1673 weakly suppresses
- L6:1532 weakly suppresses
- L5:1688 weakly excites
- L0:1301 weakly suppresses
- L4:2633 weakly excites
- L6:833 weakly excites
- L5:94 weakly suppresses
- L0:2535 weakly suppresses
- L7:1202 weakly suppresses
- L4:487 weakly excites
- L7:1676 weakly excites
- L0:178 weakly suppresses
- L7:498 weakly excites
- L0:1224 weakly suppresses
- L4:133 weakly excites
- L3:456 weakly suppresses
- L2:1481 weakly excites
- L5:460 weakly suppresses
- L4:2404 weakly excites
- L1:1347 weakly excites
- L5:374 weakly suppresses
- L4:2654 weakly suppresses
- L7:1225 weakly excites
Feeds later layers
- L10:647 suppresses
- L10:419 weakly suppresses
- L13:786 weakly suppresses
- L12:2874 weakly suppresses
- L16:2676 weakly suppresses
- L14:2582 weakly excites
- L11:2812 weakly excites
- L11:2416 weakly suppresses
- L12:1077 weakly excites
- L15:1014 weakly excites
- L13:2293 weakly suppresses
- L9:643 weakly excites
- L13:371 weakly excites
- L18:2461 weakly suppresses
- L17:1221 weakly suppresses
- L22:997 weakly excites
- L10:2777 weakly suppresses
- L9:1490 weakly excites
- L11:2007 weakly excites
- L14:1757 weakly excites
- L23:1378 weakly excites
- L25:3057 weakly excites
- L17:641 weakly suppresses
- L9:2676 weakly excites
Activation histogramA chart of how often a neuron takes each activation value.
How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.
Logit lensReading which output tokens a neuron pushes toward or away from, straight off its output weights, before the later layers have their say.
The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layersOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. instead.
Promotes
- ergy
- rometer
- lease
- legation
- egral
- ucose
- actus
- illin
- losion
- lems
Suppresses
- \Blueprint
- 晦
- currentUser
- ija
- .SaveChanges
- caret
- tracks
- penet
- ghi
- цов