unclear: 'all', 'little' and 'small' in emphasis

What this neuron does

It fires weakly on words like 'all', 'little' and 'small' in phrases that emphasise or play down an amount, such as 'Strangest of all' or 'every little change'. The pattern is faint and inconsistent. Turning it down made the text collapse into repeated 'and, or' lists.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

   and the telescope) can see. Those objects are getting farther away all the time because the universe is expanding, and moreover the expansion is accelerating. Strangest of all, the luminous matter of the galaxies—everything we see shining in the

2. #2 peak

   a significant contribution of common sequence variants to the phenotypic variability of common disease4,5⏎. Taken together, these observations have led to the evolution of the Common Disease / Rare Variant

3. #3 peak

   беспартийная система⏎5) a right of voting e) гражданин государства⏎6) district court f) гражданские и уголовные дела⏎7) a resident of the state g) правительство⏎8

4. #4 peak

   keeping yourself in a position of power by making the people under you disagree with each other so that they are unable to join together and remove you from your position A small minority have continued to govern by a policy of divide and conquer.⏎

5. #5 peak

   when he was a kid. All you have to do is find a piece of paper and use your imagination to draw

6. #6 peak

   you wish to move up, you’ll need to prove again and again that you know how to navigate technology. Sometimes, having that little bit of extra knowledge can really make a difference in your salary and lifestyle down the

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

   18th century, to Peter I?⏎Professor Andrzej NOWAK: One could draw three lines along which this phenomenon develops. The first, probably the oldest, is connected with the hope of converting the Orthodox Moscow,

2. #2 peak

   8 note) who remarks: — "Um dies (i.e. Varro's description of the extent of Roma quadrata) mit dem unten erörterten Pomerium und der Auffassung des Dionys. I 8

3. #3 peak

   ifism among its electorate, let alone industrial backwardness. It was in essence a warfare state, organized around the successful prosecution of war, albeit of a very specific kind (a new kind of machine-based conflict).⏎The background to Britain’s entry

4. #4 peak

   no longer match the original. Another case is where we need to authenticate some data, i.e. produce a kind of integrity check that only a party with a given private key could produce. (In this case, the general solution is to combine

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.