INDEX

Explanations

the followed by specific nouns

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 there

-1.86

it

-1.75

by

-1.63

of

-1.54

those

-1.44

 yalnızca

-1.41

霎

-1.37

姈

-1.34

扪

-1.33

 glimmer

-1.32

POSITIVE LOGITS

 olika

1.59

 hvil

1.48

and

1.45

 bluse

1.39

 being

1.38

 this

1.37

 frigo

1.37

 chví

1.35

现在

1.34

Activations Density 0.194%