INDEX

Explanations

no- prefix

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

 fær

-0.84

 hulle

-0.84

 hvordan

-0.82

 tirs

-0.81

руем

-0.80

scraper

-0.80

adilan

-0.79

 أو

-0.79

 FERR

-0.79

UpdateDate

-0.78

POSITIVE LOGITS

 margins

0.98

 gutter

0.86

 dragging

0.83

 focus

0.82

Děkuji

0.81

translate

0.81

 described

0.79

 showing

0.78

 mobile

0.77

 annoying

0.76

Activations Density 0.015%