INDEX

Explanations

configuration keys and variables

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

 with

-1.41

をはじめ

-1.38

贋

-1.32

もありますが

-1.31

はある

-1.30

いただけます

-1.27

oys

-1.26

')){

-1.25

kanı

-1.22

 verrez

-1.22

POSITIVE LOGITS

 dergleichen

1.63

 wahrscheinlich

1.41

1.38

This

1.37

1.30

1.29

For

1.29

 offensichtlich

1.27

Activations Density 0.011%