INDEX

Explanations

content beginnings

The neuron activates on standalone numeric tokens (i.e. numbers).

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

～

-1.88

 Since

-1.81

 Numerous

-1.79

by

-1.76

-1.72

when

-1.72

 While

-1.70

 That

-1.69

 Much

-1.69

POSITIVE LOGITS



1.83

 .........

1.82



1.81

入る

1.78

呶

1.76

 ........

1.73

<bos>

1.63

 tailles

1.62

惴

1.61

ck

1.60

Activations Density 0.000%