end of a document (end-of-text token)

What this neuron does

This neuron responds to the invisible marker the model uses to separate one document from the next. It is strongest right at that break, where one unrelated piece of text ends and another begins. Turning it up gave broken or off-topic text.

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 activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

1. #1 peak

   rounded to the nearest integer.<|endoftext|>Christine Duncan, MD⏎Sickle cell disease (SCD) affects as

2. #2 peak

   1,700.<|endoftext|>Risk assessment for construction⏎The Construction (Design and Management) Regulations (CDM

3. #3 peak

   , 2012<|endoftext|>Some weather conditions are simply not fun to ride in. As cyclists, windy days

4. #4 peak

   718<|endoftext|>Women who have kids later on in life may live longer, according to the findings

5. #5 peak

   :<|endoftext|>Copyright © University of Cambridge. All rights reserved.⏎'Aim High' printed from

6. #6 peak

   :<|endoftext|>The hamstring muscles – the biceps femoris, semitendinosus,

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

   often so excited to post<|endoftext|>Chapter 16 Risk Management for Drugs and Biologics in the United States Chapter 16RISK MAnAgEMEnT FOR DRugS AnD bIOLOgICS In THE unITED

2. #2 peak

   morning rations were of bread,⏎A slice of sinking meat,⏎Which hunger made us soon devour,⏎And ever lasted sweet.⏎At night we had a little soup,⏎Some water bolled with peas,⏎And then we took our prison beds,⏎To

3. #3 peak

   wolves.⏎tAsAM ruditashabdena gavAM haMbhAraveNa cha |⏎vrajasyotthApanaM chakrurghoShavR^iddhAH samAgatAH

4. #4 peak

   Myeloma||A type of blood cancer that hits the plasma cells of bone marrow. Myeloma cancer cells make abnormal antibodies.|⏎|Leukemia||A type of blood cancer, starts in the bone marrow, and is often associated

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.