INDEX

Explanations

foreign languages and statistics

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

it

-2.30

-1.57

ofing

-1.54

 then

-1.52

 abiye

-1.51

;",

-1.47

cers

-1.45

咵

-1.42

 döner

-1.42

 ailes

-1.40

POSITIVE LOGITS

of

1.98

for

1.78

 Penelitian

1.45

чатки

1.44

 siempre

1.43

 Mereka

1.42

 jejich

1.35

 вони

1.34

 всегда

1.30

Either

1.30

Activations Density 0.099%