'to' after 'reason' or 'how and when'

What this neuron does

This neuron fires on the word 'to' right after phrases like 'no reason to' or 'learn how and when to', where an infinitive is about to follow. Turning it up gave text that did not clearly change theme, and turning it down produced number lists and quiz-style text, so the link to the trigger 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

   12.054 of the Texas Property Code governs judicial<|endoftext|>Adjustment to college life after school is always a challenge for young adults. One reason to be unsuccessful in navigating stress, depression, anxiety during college days is that the maturity

2. #2 peak

   of the planet relies on these cloud fortresses, and will do so even more in years to come. Remarkable as the cloud is, there is no reason to think it is anywhere near completion. The generation of data and the need for its

3. #3 peak

   . (June 2009) (Learn how and when to remove this template message)|⏎The Central Business District as seen from the top of

4. #4 peak

   ., a client and server)⏎talking to one another, we have only one channel of communication. Clearly,⏎we need more than two entities. It seems unreasonable to require a hundred⏎Looking into millennia of human uses of trust, we realize that

5. #5 peak

   glucagon emergency kits for home and school.<|endoftext|>|This article needs additional citations for verification. (July 2012) (Learn how and when to remove this template message)|⏎Sendust is a magnetic metal powder that was invented

6. #6 peak

   people reading this have reached an age where fat either is, or may potentially be, a problem, it’s worth stating that there’s actually no biologic reason to get f

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

   , England's Farnborough Airshow. Click here to read an MIT News Office story on the glider, here to read about the award, and here to check out the project homepage.<|endoftext|>Since 1993, RAN

2. #2 peak

   release and endoscopic surgery.⏎(Click Carpal Tunnel Syndrome to learn more, including what causes the condition and who is most at risk for it. You can also click any of the links in the box to the right for specific information.)<|endoftext|>

3. #3 peak

   by Dr Gemma Catney, Professor Richard Wright, and Professor Mark Ellis. The original article, posted in Geography Directions, can be accessed here. You can also read the full article published in Transactions of the Institute of British Geographers here.⏎

4. #4 peak

   world of nature. We believe that children who learn to love our Earth⏎today will protect it tomorrow.⏎On our web site, you can look at our books and find out how to order them. In⏎you¡¯ll find fascinating information

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.