INDEX

Explanations

total of numbers

The neuron fires on numeric tokens (quantities, counts, percentages, etc.).

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

-2.16

or

-2.03

if

-1.98

For

-1.98

of

-1.86

它

-1.77

on

-1.75

for

-1.71

 This

-1.71

POSITIVE LOGITS

コロナ禍

1.84

 ſou

1.81

今後も

1.78

 différents

1.77

ナイキ

1.74

 juſ

1.73

その時

1.71

メルカリ

1.71

ユニクロ

1.70

 accompagner

1.70

Activations Density 0.032%