INDEX

Explanations

correctness or legitimacy of states

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

hey

0.92

you

0.87

 statesmen

0.86

you

0.84

unuz

0.81

carriers

0.79

anız

0.79

 שמ

0.79

ದ

0.78

و

0.78

POSITIVE LOGITS

Rin

1.17

 seharusnya

1.16

 мою

1.11

 Valerie

1.07

 Juli

1.07

 Lili

1.07

 мои

1.06

 Tori

1.05

 Koval

1.03

 Deve

1.00

Activations Density 0.354%