end-of-document token after a finished text

What this neuron does

This neuron mostly reacts to the invisible marker that signals the end of a document, which appears right after a text finishes and a new unrelated one begins. When pushed down, it produced some vivid, dramatic wording, but the link is weak.

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

   and idiomatic expressions. New Amigos also includes geographical information and cards focused on culture, business, and food and drink.⏎New Amigos is a great game<|endoftext|>How did the kindly Christian saint, good Bishop Nicholas, become a roly-p

2. #2 peak

   melanoma.⏎This fact sheet from the National Cancer Institute explains the subject thoroughly. It also lists a number of the clinical trials currently underway on experimental therapeutic vaccines.<|endoftext|>What Are PK Boosters?⏎Just like with anything, gardening and⏎PK Booster

3. #3 peak

   and Emerging Technologies Flagship competition launched by the European Commission, the other one being the “Graphene” project led by Swedish theoretical physicist Jari Kinaret.<|endoftext|>

4. #4 peak

   .⏎A weekly sampling of articles, blogs and reports relevant to TT educators.⏎Student pushback against mixing up their lunchtime seating can be a perfect teaching opportunity.<|endoftext|>Everyone on the World Wide Web is talking about SSL certificates. And has been doing

5. #5 peak

   elementary version of the highly-successful program.⏎Additional Meeting Notes⏎There are a limited number of speaking slots. It is a first come, first served system.<|endoftext|>Fast Food Near Urban Schools Causes Obesity In Minority Children?⏎Does Fast Food Near Urban

6. #6 peak

   .⏎We traveled all this days and night,⏎Oppressed by dust and heat;⏎We got some muddy water,⏎But nothing for to eat.⏎At length each man<|endoftext|>Since 199

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

   2 BC to 1323 BC. He is widely regarded as King Tut. When his tomb was discovered in 1922, the world stopped to witness the artifacts and the mask.⏎Last century, several bodies were found in

2. #2 peak

   the paper, and mammal collections manager at the Field Museum, Chicago, US, said hearing the news that the monkey belonged to a new genus "sent shivers down my spine".⏎"Simply put, the genetics said that it was closely related

3. #3 peak

   150 minutes of exercise a week, though it explains this might be 20 to 60 minutes of vigorous exercise – which makes you huff and puff, such as jogging, aerobics, football and netball –

4. #4 peak

   they were doing what was best for them. As a parent, my heart goes out to those adults.⏎Unpasteurized, or "raw," milk,

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.