document boundary separator token

What this neuron does

This neuron fires most strongly on the hidden marker that separates one web page from the next in the training text, right where an abrupt change of topic happens. Its negative side is code and listings. Turning it up or down gave odd, loose text with no clear theme.

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

   00<|endoftext|>The reasons and urgency that lead a group of people to just up and leave a

2. #2 peak

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

3. #3 peak

   requires a bit better understanding of color<|endoftext|>ORLANDO, Florida — The curse of the mummy may truly be fatal

4. #4 peak

   environmentally incompatible.<|endoftext|>Dhyunsar Mahadev Temple is a major Hindu temple located in the

5. #5 peak

   needed around planes en route to keep them safely separated.<|endoftext|>FEDERAL Hill House is a squat building in central Providence, within earshot

6. #6 peak

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

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

   :⏎void * memchr ( const void *, int, size_t );⏎instead of the two overloaded versions provided in C++.⏎/* memchr example */⏎int main ()⏎char * pch;⏎char str = "Example string";⏎pch = (char

2. #2 peak

   ⏎> 2 if n> 10⏎> 3 print "This might take a while..."⏎> 4 for i = 1 to n⏎> 5 for j = 1 to i⏎> 6 print

3. #3 peak

   anyway :P)⏎void genFactorial(int x, int t)⏎int total = t; // you probably wouldn't even need total now⏎void main(void) //<|endoftext|>Splattered Plants Should Serve As A Reminder⏎By Phran Novelli

4. #4 peak

   a sacred religious ceremony, in South Dakota this past summer.⏎Complete information about survivors could not be confirmed<|endoftext|>A simple example of HTML is:⏎<HTML> <HEAD> <TITLE>This is the Title</TITLE> </HEAD> <BODY

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.