INDEX

Explanations

useful usable

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

useful

-1.65

 useful

-1.55

 Useful

-1.30

 usable

-1.21

 útil

-1.14

 utile

-1.14

Useful

-1.13

 útiles

-1.05

 utiles

-1.00

usable

-0.96

POSITIVE LOGITS

0.90

ness

0.68

 propOrder

0.59

ity

0.57

ance

0.54

itarian

0.54

er

0.52

ers

0.52

ities

0.52

 unknownFields

0.52

Activations Density 0.108%