INDEX

Explanations

mathematical expressions or sequences

The neuron activates on numeric tokens (digits and numbers) in mathematical sequences or expressions.

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

尔

-1.64

糴

-1.61

 背影

-1.57

 土産

-1.54

 schreck

-1.50

 Размер

-1.46

 sauvages

-1.44

arj

-1.44

 agarre

-1.43



-1.42

POSITIVE LOGITS

of

2.55

 with

2.02

1.78

we

1.70

1.66

For

1.66

 because

1.56

The

1.52

 used

1.51

ol

1.49

Activations Density 0.093%