person names and role nouns

What this neuron does

This neuron responds to words that name a person or a role, like 'queen', 'manager', 'mother', a person's name, or a company's leader. When it was turned up, the model drifted toward talking about people and their situations.

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

   about the universe is wrong. Physicist and best-selling author Brian Greene takes you on a journey that bends the rules of human experience.⏎BRIAN GREENE (Columbia University): Why don't we ever see events unfold

2. #2 peak

   Dr. Nuha El Sayed, vice president of Healthcare Improvement at the American Diabetes Association. Hi, thanks for joining me.⏎Dr. Nuha El Sayed: Thank you for having me.⏎So, today I would love to pick your

3. #3 peak

   2008 Express Edition >> Visual Studio Tools >> Visual Studio 2008 Command Prompt (Run with administrator privileges)⏎- Once you are in the command line, you can use any editor such as edit to write a C program.⏎

4. #4 peak

   reaction to this paragraph?⏎The king neglected his wife?⏎He drank too much?⏎The Queen was busy with her own guests?⏎Put yourself in the place of the queen if you are female, the place of the king if you are male. How

5. #5 peak

   synopsis of the first video in the series written by a guest on this blog, Roni Jacobson, a science journalist based in New York City.⏎By Roni Jacobson⏎Being unable to recall a word on

6. #6 peak

   maximising costs and power savings - a critical challenge to overcome for the success of any exascale initiative," said Vishal Dhupar, managing director of NVIDIA India.⏎The development of exascale computing systems, which would be hundreds of

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

   however freely search the site and view the abstracts and keywords for each book and chapter.⏎If you think you should have access to this title, please contact your librarian.⏎To troubleshoot, please check our FAQs, and if you can't find

2. #2 peak

   of Frank Churchill’s secret engagement to Jane.⏎“Good God!” cried Emma, “Jane actually on the point of going as governess! What could he mean by such horrible indelicacy? To suffer her to engage herself — to

3. #3 peak

   abstracts and keywords for each book and chapter.⏎If you think you should have access to this title, please contact your librarian.<|endoftext|>Information on creating school gardens for outdoor learning, compiled by the National Clear

4. #4 peak

   is for Gertrude to try and determine what is going on with Hamlet. She starts out on the offensive, accusing him of offending his (step-) father, Claudius. Hamlet is already in high spirits having just missed an opportunity

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.