INDEX

Explanations

formal writing

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

GS

-0.66

gs

-0.52

bois

-0.50

ISE

-0.50

maksud

-0.50

GS

-0.49

rams

-0.48

ycle

-0.48

galus

-0.47

yos

-0.47

POSITIVE LOGITS

aarrggbb

0.73

 незавершена

0.71

 Meksiku

0.70

ⓧ

0.68

 autorytatywna

0.68

 Italijanski

0.66

#+#

0.65

+#+#

0.65

 ModelRenderer

0.64

 Roskov

0.64

Activations Density 0.016%