INDEX

Explanations

mathematical notation and symbols

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

ので

-1.04



-1.03

 kalla

-1.02

 dito

-0.94

!}

-0.94

GLenum

-0.92

so

-0.92

 cái

-0.91

čo

-0.91

puo

-0.88

POSITIVE LOGITS

時々

1.02

 berücksich

0.94

変わらず

0.92

沢山

0.90

—.

0.89

新た

0.89

願意

0.88

 mudança

0.88

 мальчика

0.88

 jednej

0.87

Activations Density 0.001%