INDEX

Explanations

verification and proof assistants

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

 ziet

-1.31

End

-1.16

亲自

-1.15

 сере

-1.13

₤

-1.10

や

-1.07

ם

-1.05

cantara

-1.05

 [''],

-1.05

lida

-1.05

POSITIVE LOGITS

‫

1.34

 neceff

1.33

Ĭ

1.27

:""

1.27

حيان

1.25

pæ

1.23

 meras

1.23

:>

1.20

ություն

1.20

 both

1.20

Activations Density 0.027%