INDEX

Explanations

was released/planned/named

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

ᥬ

-1.70

۸

-1.59

这也是

-1.46

НАЯ

-1.45

何况

-1.41

这也

-1.41

*"

-1.41

鹛

-1.36

最后由

-1.36

."

-1.35

POSITIVE LOGITS

are

1.62

 recognised

1.36

現

1.34

 lengte

1.33

 иной

1.32

 galima

1.30

有點

1.30

droje

1.30

mathrm

1.26

Activations Density 0.020%