INDEX

Explanations

mathematical notation variables

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

Ө

-1.59

sbereich

-1.46

romas

-1.43

ợn

-1.39

通常

-1.39

OBJ

-1.38

λους

-1.37

órica

-1.36

ACIÓN

-1.35

-1.34

POSITIVE LOGITS

すぎた

1.72

Estás

1.52

すぎて

1.47

他の

1.45

部分が

1.45

 jego

1.45

 inaweza

1.44

 ambayo

1.42

就此

1.39

蘑菇

1.38

Activations Density 0.073%