end-of-text boundary tokens

What this neuron does

This neuron fires on the invisible marker the model uses to show that one document has ended and another begins. Turning it up made the model fall into repeating the word 'either', and turning it down gave repetitive talk about plots.

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

   locate.<|endoftext|>Science Fair Project Encyclopedia⏎The World Factbook⏎The World Factbook is an

2. #2 peak

   Project:<|endoftext|>After years of experience and "combing through" catalogs⏎to find the best

3. #3 peak

   that<|endoftext|>After splitting genetically from wolves about 135,000 years ago

4. #4 peak

   data from TC1.<|endoftext|>The concept of welfare state⏎We all know that most of the modern democratic countries

5. #5 peak

   to like.<|endoftext|>The late Dominica-born writer Jean Rhys, best known for her novel “

6. #6 peak

   -Pecos.<|endoftext|>top of page⏎Patterns of tree-liana interactions: distribution and host preference of

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

   conuts and banana leaves<|endoftext|>const void * memchr ( const void * ptr, int value, size_t num );⏎void * memchr ( void * ptr, int value, size_t num );⏎Locate character in block

2. #2 peak

   from some neighborhoods and into others.⏎1. A storage unit designed to hold various objects.⏎2. To cause a structure to shift so that it is out of plumb.⏎1. A force that causes a structure to shift so that it is

3. #3 peak

   who it was that posted it, and I can't see just now anyway :P)⏎void genFactorial(int x, int t)⏎int total = t; // you probably wouldn't even need total now⏎void main(void) //<|endoftext|>

4. #4 peak

   x80;⏎P0 = 0x98;⏎P0 = 0xC0;⏎P0 = 0xff;⏎} while(1); // Endless loop<|endoftext|>Wisconsin Well Water: Planning Web-Based⏎Resources to

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.