INDEX

Explanations

words starting with s

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

 Activ

-0.87

PRI

-0.82

懾

-0.80

 puree

-0.78

ecturer

-0.78

 Machiavelli

-0.78

 coiff

-0.75

 delicacy

-0.73

 vechi

-0.72

年以上

-0.72

POSITIVE LOGITS

1.20

stateParams

0.78

arikat

0.77

 understated

0.76

 creen

0.72

 delas

0.69

 ucran

0.69

 Weir

0.68

Citations

0.68

stered

0.68

Activations Density 0.022%