end-of-text marker between documents

What this neuron does

This neuron fires on the invisible end-of-text marker that appears where one web page abruptly joins the next. It is most negative on code and markup symbols such as ";", "(" and HTTP header words. Steering produced ordinary text with no clear link to the pattern.

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

   ’t embark on any new diet restrictions without a doctor’s supervision if you are ill, pregnant or breastfeeding, or if you know that you have serious allergies.⏎Basically<|endoftext|>All scientific knowledge is uncertain. This experience with doubt and uncertainty is important. I

2. #2 peak

   's global environment for promoting peace and non-violence among mankind."<|endoftext|>Processing nodes in a graph one at a time, usually in some specified order.

3. #3 peak

   $50 from the mint."<|endoftext|>In the next of our blog posts for Census week, we showcase recent research undertaken

4. #4 peak

   historical data will only make sense when used in a chosen perspective by a given scholar.⏎Conversely, any scholar working on a given topic will find far greater<|endoftext|>Fifth Street Southeast Historic District⏎Boundaries:

5. #5 peak

   The length of a day normally changes anyway by<|endoftext|>A long time ago I wrote the article The Dull Case of Emissivity

6. #6 peak

   opportunity that would help sustain the museum long-term.⏎<|endoftext|>“A 200:1 ratio is very difficult to overcome,” said D

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

   <polygon points="200,10 250,190 160,210" style="fill:lime;stroke:yellow;stroke-width:1"/> </svg>⏎Here is what the

2. #2 peak

   an exception, which is life as usual for a Python programmer.⏎if not server_response['successful']:⏎etag = server_response['file_handle'].info().getheader('ETag')⏎xml_document = server_response['xml_document']<|endoftext|>Deepak V

3. #3 peak

   406 Not Acceptable response because only German and English versions of the document are available.⏎GET /news HTTP/1.1 Host: www.example.ai Accept-Language: fr⏎HTTP/1.1 <|endoftext|>The move to electronic health

4. #4 peak

   When the 406 Not Acceptable error message is received, it is in response to an HTTP request that includes a negation-related header such as Accept or Accept-Language. When the client includes one or more of these headers, the server

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.