question marks after a statement

What this neuron does

This neuron responds to a question mark that comes right after a statement, often in a short rhetorical question or a heading like "Not exactly what you need?". Turning it up made the model repeat questions about itself, though that may just be a side effect of the strong push.

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

   ION Exposure Attention Interpretation Exposure Exposure highlights the stimulus to which a consumer is exposed to. Exposure can be either deliberate or random. ...⏎Not exactly what you need?<|endoftext|>Allegany County’s

2. #2 peak

   % of behavioral intention, social norms are rarely even significant and always account for a very small percentage towards the variance of exercise intentions. ...⏎Not exactly what you need?<|endoftext|>Member of the Turkish National Allergy and Clinical Immunology Association. Lecturer

3. #3 peak

   Philae, to set down on the comet's surface to collect even more data, a feat never before attempted. That will certainly be worth watching.⏎Courtesy NASA?JPL-CaltechRemember last month when we posted a photo of the Earth and

4. #4 peak

   make sense. It has to describe something? Why then not just plain English(whatever language you choose)⏎String theory's mathematical

5. #5 peak

   to people seeking war with Iran – No!), this is crazy. First, he’s advocating for homosexually-active men to enter fake marriages. This is defending marriage? But even better, let’s take a quick look at Alexander’s marriage policies,

6. #6 peak

   and delayed the release? Provide reasons for your decision.⏎You must first post your answer(s) before you

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

   lower Columbia sturgeon: not enough juveniles.⏎“Annual recruitment of sturgeon —new st<|endoftext|>Can a small camera possibly have a large lens in the front?⏎There are really "large" lenses. This search is not the biggest one,

2. #2 peak

   York, Philadelphia, Baltimore and Washington, D.C., as well as in Florida and some Southern states.⏎Don’t Hebrew Israelites have a community in southern Israel?⏎One part of the wider Black Hebrew Israelite movement began arriving in Israel in the

3. #3 peak

   and high school students)⏎- Undergraduate education: The Summer Undergraduate Research Experience (SURE) program at Washington State<|endoftext|>Is Soil A Heterogeneous Mixture?⏎Whether you’re a keen gardener already or you’re a complete beginner, understanding

4. #4 peak

   6 Printable – Maps is an crucial supply of principal information and facts for historical examination. But just what is a map? This is a deceptively simple query, before you are motivated to provide an

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.