the word 'one' as a pronoun

What this neuron does

This neuron lights up on the word "one" when it is used as a pronoun, as in "one of the biggest factors" or "one another". When it was turned up, the model's output fell into loops of words like "have" and "are" or odd phrases, which doesn't clearly point to a single theme.

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

   , Auditable, and Transparent Elections):⏎[N]o matter how hard one looks for errors or faults in voting system software, there is no way to guarantee that one has found them all. Even if no errors or faults

2. #2 peak

   . (of positions, functions, ranks, etc.) unable to be held simultaneously by one person.⏎6. Med.of or pertaining to biological substances that interfere with one another physiologically, as different types of blood in a transfusion.⏎7

3. #3 peak

   Pharm.of or pertaining to drugs that interfere with one another chemically or physiologically and therefore cannot be mixed or prescribed together.⏎

4. #4 peak

   England officially recognizes the colonies to be in rebellion and that they will take all steps necessary to bring the traitors to justice⏎Colonists sends of a ___as one

5. #5 peak

   so rare that generations of men and women never live to see one, and so significant it enabled astronomers armed with telescopes and trigonometry to

6. #6 peak

   have scars and blemishes on it. These scars and blemishes are usually a result of a skin condition or a disease that has a skin condition as one of its components. Acne is a common skin condition that causes permanent marks to

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

   or string- particle or triangle- particle? No, Euler's formula has quantity (pi) which says me that the particle must be only a circle . Now I want to understand the behavior of circle - particle and therefore I need to use spatial

2. #2 peak

   of a lego brick⏎- Number of bricks needed = volume of planet Earth / volume of a lego brick⏎We will need to use the following two formulas:⏎You can now code this algorithm using

3. #3 peak

   Writer John Byrne maintained modest abilities for the speedster character Danny Hilltop in his series John Byrne’s Next Men. Although Danny can keep pace with a race<|endoftext|>We will talk about partial data from close to a decade's worth of data from a

4. #4 peak

   19), Portland roses (since 1792), and Boursault roses (early 1800<|endoftext|>of Romans & Retreats⏎We don't know whether there were any Romans resident in Beech Hill, but they

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.