end of document token

What this neuron does

It lights up on the invisible marker the model uses to show that one document has ended and an unrelated one begins. Its negative hits are in odd spots inside lists and citations. Turning it up made the model repeat itself and drift into unrelated topics.

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

   –6. Warsaw, 1877–82.⏎Pamiqtki Soplicy. Warsaw, 1961.<|endoftext|>Translate this page into:⏎Approach to family assessment and intervention⏎All India Institute

2. #2 peak

   9, 2002⏎Elysia from Gulf of Mexico⏎From: Anna L. Bass, October 8, 2002<|endoftext|>|Tourists visit slave cabins at Boone Hall plantation, near Charleston|⏎|Vis

3. #3 peak

   is sharp and cutting resistance is small.⏎- Excellent cutting surface roughness can be produced even when machining at low speed.⏎- Suitable for soft materials or workpieces<|endoftext|>Fernanda vertelt haar verhaal in een gesprek met CSL

4. #4 peak

   ; cultivated and adventive worldwide, including in China.⏎(Authors: She Menglan (佘孟兰 Sheh Meng-lan); Mark F. Watson)<|endoftext|>By Cary Groner⏎3D printing has been waiting to disrupt the orthotics

5. #5 peak

   a religious or educational one.⏎D<|endoftext|>Administration of Justice 104:⏎Unit Objectives: At the completion of

6. #6 peak

   affected by a bad situation⏎Savings can act as a cushion against unemployment.⏎the soft rubber edge of the table used for playing billiards or snooker<|endoftext|>I have been trying to consolidate my

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

   J.M.; Mortimer, S.R.; Brereton, T.; Redhead, J.W.; Thomas, J.A.; Pywell, R.F.. 20

2. #2 peak

   Electoral College Cnn Blank Map Best Of Top Us Election pertaining to Blank Electoral College Map 2016 Printable, Source Image : clanrobot.com⏎

3. #3 peak

   • Teacher Resources • Frequently Asked Questions • Glossary • References • Links to Other Mussel Sites⏎

4. #4 peak

   JSTOR JSTOR is part of ITHAKA, a not-for-profit organization helping

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.