INDEX

Explanations

code or sympathy messages

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 inevitably

1.27

"]

1.26

 unhappy

1.24

льм

1.24

 muit

1.21

Fre

1.21

Ки

1.18

趕

1.18

necessarily

1.16

pageToken

1.15

POSITIVE LOGITS

 공격

1.52

 می‌باشد

1.45

 Plague

1.44

 Beled

1.43

 Compost

1.41

 می‌شود

1.40

tiden

1.39

 boyunca

1.37

까지

1.36

𝒆

1.36

Activations Density 0.000%