INDEX

Explanations

struggling with difficulty or desire

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tratti

1.79

乎

1.78

1.77

rante

1.77

 lucrat

1.73

*>(

1.72

rn

1.68

bolt

1.68

राधना

1.65

sub

1.64

POSITIVE LOGITS

ంగ్

1.62

스러

1.62

iselle

1.55

इक

1.55

NonNull

1.54

ウンド

1.54

halt

1.53

peau

1.52

ปรุง

1.51

лиз

1.50

Activations Density 0.021%