end of document marker

What this neuron does

This neuron fires on the invisible marker that tells the model one document has ended and a new, unrelated one begins. Its negative side reacts to odd line breaks and quotes, and steering did not produce a clear pattern.

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

   0240.<|endoftext|>By 2003, plenty of data suggested that pesticide drift was harming

2. #2 peak

   can be used to<|endoftext|>| Trisha Sertori |⏎JUGA, Indonesia (Reuters) –

3. #3 peak

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

4. #4 peak

   ,0<|endoftext|>Guidelines for Restoring Cultural Landscapes⏎Identifying, retaining and preserving

5. #5 peak

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

6. #6 peak

   . On<|endoftext|>Anatoly Lunacharsky On Literature and Art 1909

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

   example sentence"⏎- S: (n) fire (the event of something burning (often destructive

2. #2 peak

   True, obj)". If it failed, you might return "(False, reason)". Often, you can

3. #3 peak

   a matrix⏎Find nth maximum⏎Matlab Basics II - Create a vector with a repeated entry

4. #4 peak

   for<|endoftext|>- Agriculture in NSW is important for the state’s economy, industries, communities and

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.