comma after "and" joining clauses

What this neuron does

This neuron lights up on a comma that comes right after "and" or a dash-joined "and" when a new clause starts in ordinary prose. It goes slightly negative on commas inside code parameter lists. Turning it up or down did not produce a clear theme in the replies.

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

   the class and helping the class become a successful place of learning.⏎The instructor presented a survey to the students on the first day about the merit of participation; and, how participation can affect the class.⏎The first function of the research plan focuses on

2. #2 peak

   Hebrides that Columba turned his face when he accepted the terrible penance of Molaise. He bade farewell to his relatives, and, with a few monks who insisted on accompany him whithersoever he might

3. #3 peak

   band illumination."⏎To get the performance required, however, the team needed to design a massively parallel broadband diffractive neural network for all-optical computation — and, in an example of "set a thief to catch a thief" logic, put

4. #4 peak

   “capital of the South,” a Jet Age airport promised to put what had once been a minor railroad town within a day’s reach of London and Paris – and, in the minds of some Atlantans, on the same plane of international significance

5. #5 peak

   measures, meant to treat illnesses caused by under nutrition; and, famishing measures, meant to treat those caused by<|endoftext|>Anorexia may be

6. #6 peak

   stalled acceptance and implementation of this approach, however, including a high cost of investment, molasses-slow production times, confusion about the most efficient workflows – and, as a result of such concerns, an understandable reluctance on the part of clinicians and

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

   the other code (too tired to check who it was that posted it, and I can't see just now anyway :P)⏎void genFactorial(int x, int t)⏎int total = t; // you probably wouldn't even need total

2. #2 peak

   flag... ] file... -lm [ library... ] #include <math.h> double ldexp(double x, int exp);⏎float ldexpf(float x, int exp);⏎long double ldexpl(long double x, int exp);⏎These functions

3. #3 peak

   banana leaves<|endoftext|>const void * memchr ( const void * ptr, int value, size_t num );⏎void * memchr ( void * ptr, int value, size_t num );⏎Locate character in block of memory⏎Searches within the

4. #4 peak

   The range() function returns a sequence of numbers starts from a given number to another given number with a given step.⏎It is defined as like below:⏎range(start, stop, step)⏎- start is

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.