"about" in "what about" questions

What this neuron does

This neuron responds to the word "about" when it follows "What" in a follow-up question, like "What about the future?". Turning it up gave wandering text that did not clearly show this 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

   just wasn’t much technological or scientific progress at that time.⏎What about the first decade of the 20th century? That’s easier. The

2. #2 peak

   Fight⏎Donate today to preserve Civil War battlefields and the nation’s history for generations to come.<|endoftext|>Understand the True Health Benefits of Almonds⏎What about the health benefits of almonds? Almonds are healthy nuts and are loaded with many

3. #3 peak

   the hearing aid is hard to remove, use a slightly damp, clean cloth. Do not use soap, rubbing alcohol or cleaning products on your hearing aids.⏎What about liquids and substances besides water?⏎Avoid exposing the hearing aid to hair products and makeup

4. #4 peak

   just the scraps from food preparation that should be added to the heap. What about the pieces of paper, card etc that we rip up for (hopefully) recycling

5. #5 peak

   nationalisation. But less has changed politically. The party - based on the Soviet model - runs the country in much the same way it has always done.⏎What about the future?⏎Some believe the opening up of China's economy will eventually lead to

6. #6 peak

   majority of the studies, folks don’t get any crazier around the full moon–despite the many books and movies attesting to it.⏎Anyway, what about the link between a woman’s menstrual cycle and the lunar cycle? I mean,

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

   few monks who insisted on accompany him whithersoever he might go, launched his frail currochs from the northern shore. They landed first, or rather were carried by wind and stream, upon the little isle of Oronsay

2. #2 peak

   udate winter look!<|endoftext|>While doing my own comparison of women in the New Testament and Josephus’ Jewish histories, I began to notice a theme, or rather, two themes. Each one dealing with customs involving women and since I could not

3. #3 peak

   of the painter Charles Gleyre (1806 – 1874) (Gleyre Marc-Gabriel trained students such as Renoir, Monet, Sisley), he attended from 1875

4. #4 peak

   and could easily be a lot more (I'm assuming here that the minimum impact speed is 11 km/sec, Earth's escape velocity; it could in fact be much higher). This probably would not cause an extinction level event for humans,

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.