INDEX

Explanations

list-like structures or citations

The neuron fires on numeric constants—especially multi‐digit or floating‐point literals—in code examples.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

なども

-2.11

 także

-1.77

だけでなく

-1.70

 также

-1.64

 גם

-1.61

 ก็

-1.59

 également

-1.54

≍

-1.54

 επίσης

-1.52

鲞

-1.50

POSITIVE LOGITS

 having

1.84

 their

1.71

 using

1.68

 that

1.64

 trying

1.59

When

1.59

one

1.55

 giving

1.54

 после

1.54

Activations Density 0.028%