comma after a vocative or lead-in

What this neuron does

This neuron fires on a comma that comes right after a short lead-in, such as a name being addressed ("Why would I do that, Marcus?"), an exclamation ("Great work, Shipmates!") or a quoted speaker. Turned up, the model fell into repeating words like "my dear" and "Ms.". The negative side is mostly C code with "void" pointers.

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

   in My Garden”, beloved local garden guru Carolyn Singer wrote, “’Grandma, why don’t you grow yucky flowers?’ ‘Why would I do that, Marcus?’ I asked, respectful of his three-year-old wisdom. ‘Well,’

2. #2 peak

   .⏎Resilience is his middle name.⏎Here circumstances are presented as clouds that help trouble and strife to germinate and proliferate.⏎‘This is the world, and we cannot expect to give many hours to pleasure – Circumstances are like

3. #3 peak

   , as a way of depicting his self-grandeur. In one of her books, another character asks him about it:⏎- Dr. Lutz: Tell me, why do you insist on referring to yourself in the third person? It's intensely

4. #4 peak

   start through direct mail solicitations. "The shriller you are, the better it is to raise money," explained co-founder Terry Dolan.⏎N

5. #5 peak

   said Guillaume Gronoff, a French astrophysicist at NASA Langley.⏎"And you think, 'OK, what I am looking at — it's a<|endoftext|>An ultra-

6. #6 peak

   makes you wonder why Moses included it where he did, or at all. And even more, "Why, now is this seemingly obscure story from the Book of Genesis not only included in 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

   conuts and 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

2. #2 peak

   same to a compiler:⏎As humans though, the above is a lot more like gibberish.⏎void * load_model_from_disk(const char *);⏎void draw_model(void *, float, float, float);⏎void deallocate_model(void *);⏎And that is

3. #3 peak

   ptr.⏎If the value is not found, the function returns a null pointer.⏎In C, this function is only declared as:⏎void * memchr ( const void *, int, size_t );⏎instead of the two overloaded versions provided in C++

4. #4 peak

   is recorded in several Roman mosaics.⏎The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept"

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.