INDEX

Explanations

easy to

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

遠慮

-1.30

to

-1.30

it

-1.30

by

-1.27

倘

-1.24

 agrícolas

-1.22

 tekrar

-1.21

恥ず

-1.20

 saludables

-1.16

 это

-1.13

POSITIVE LOGITS

 will

1.38

him

1.33

ngOn

1.27

 people

1.26

='',

1.24

 використовувати

1.23

 человеку

1.23

 kilomètres

1.22

ösungen

1.22

öte

1.19

Activations Density 0.045%