modifiers right before a noun

What this neuron does

This neuron fires on words that come just before the noun they describe, like "surrounding" in "surrounding region" or "daily" in "daily exposure". The pattern is loose, and turning it up mostly gave rambling or repetitive text, so the link to any clear theme is weak.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

1. #1 peak

   stratified by region and compared with those of a national sample of comparably aged students from the Monitoring the Future study. Specifically, lifetime and last 30-day self-reported

2. #2 peak

   completely avoided.⏎However, overcuring can become a problem when the 3D model contains a hole or cavity in its z axis, i.e. its vertical direction. At the moment when this cavity is closed, there is no previous layer

3. #3 peak

   % to 80%. Typically a fracture can be seen on ultrasonography as a disruption in the hyperechoic linear cortex of bone as well as surrounding hematoma. (See image 1.) Ultrasonography of the pediatric elbow

4. #4 peak

   7.4 years). American Indian students reported significantly higher lifetime and last 30-day substance use rates compared with the national sample. Lifetime use rates for American Indian students

5. #5 peak

   Adobe Acrobat Reader version 10 or higher for the best experience.⏎- What challenges do LEAs face related to school physical security?⏎A core responsibility of the local education agencies (LEAs) that operate kindergarten-through–12th grade (

6. #6 peak

   n (‘Afrin in Arabic), with an urban population of approximately 80,000. The city of Efrîn and the surrounding region have a population of close to 500,000.

Steering

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.

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

1. #1 peak

   Weather Radio.⏎| || |⏎ORIONID METEOR UPDATE: Earth is passing through a broad stream of debris from Halley's Comet, source of the annual

2. #2 peak

   pass through a large iron gate that marks the border.⏎The Nathula Pass, once part of the ancient Silk Road and later sealed after a 1962 war, was reopened in 2006 as a symbol of improved relations

3. #3 peak

   to Tolkappiam it is learnt that the great sage Agastya brought all the 18 clan of Velirs to the south after some kind of natural calamity struck the northern part of the country on those days, most importantly the

4. #4 peak

   to leave the video in its raw state. You will probably discern why.]<|endoftext|>On Scotland’s Isle of Skye, scientists have identified two areas with evidence of ancient life forms.⏎Researchers believe the markings are, in fact, footprints from dinosaurs

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Activation histogram

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 lens

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 layers instead.