INDEX

Explanations

assignment and return statements

The neuron strongly activates on numeric literals—especially floating-point numbers with decimal points—wherever they appear in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

❖

0.59

}_{\

0.56

日报

0.55

㶲

0.55

 सभाग

0.54

委员会

0.52

 ntawm

0.52

 בס

0.51

 घालून

0.51

 나오는

0.51

POSITIVE LOGITS

"";

0.72

ز

0.61

("");

0.61

'';

0.60

 '.';

0.58

 Integer

0.57

{};

0.57

(".");

0.56

 botao

0.55

Activations Density 0.000%