INDEX

Explanations

by followed by action or description

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[{{

1.52

[{

1.33

érien

1.31

dealing

1.29

|}

1.27

-*-

1.26

érateur

1.25

}}$,

1.25

RECTION

1.24

 관련된

1.22

POSITIVE LOGITS

far

2.04

 default

1.81

 sheer

1.65

 definition

1.59

way

1.54

 contrast

1.54

绝对

1.53

 necessity

1.51

 virtue

1.48

 invitation

1.44

Activations Density 0.179%