unclear: document boundary tokens

What this neuron does

This neuron is weak and hard to pin down. Its strongest responses fall on the invisible end-of-document marker where one web page joins another, plus a few random words. Turning it up gave unrelated text, so there is no clear story here.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

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

2. #2 peak

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

3. #3 peak

   0 International<|endoftext|>POWER IN AC CIRCUITS⏎Power of a circuit is defined as the

4. #4 peak

   compost in a<|endoftext|>In the Middle East and North Africa (MENA), women have made progress toward

5. #5 peak

   Louisiana back to France (1800). U.S.A. purchases Louisiana (1

6. #6 peak

   0 mph)<|endoftext|>Today I wondered which NT books relied more heavily on the Septuagint vs

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

   send, (and hopefully, receive), a valentine.⏎In the 1840

2. #2 peak

   xA4;⏎P0 = 0xB0;⏎P0 = 0x99;⏎P0

3. #3 peak

   easy as with other programming languages.⏎To create a list of integers, create a new variable and:⏎That’s simple right? And that wasn’t possible with Record Lists.⏎Creating a list of a single compound type like Entity or Structure, was

4. #4 peak

   table with a specific name or index exists.⏎The following example retrieves a single table by name from the DataTableCollection.⏎Private Sub GetTableByName() ' Presuming a DataGrid is displaying more than one

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.