INDEX

Explanations

allegedly or who followed by an action

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

 rencont

-0.96

スポンサーリンク

-0.95

 dégust

-0.91

 أيض

-0.90

おはよう

-0.88

 étend

-0.87

ércoles

-0.87

 clô

-0.86

 subli

-0.86

 forfe

-0.84

POSITIVE LOGITS

 steal

1.57

 stole

1.52

 sexually

1.50

 vandal

1.43

 embe

1.42

 theft

1.41

 graffiti

1.37

 punch

1.34

 assault

1.34

 insult

1.33

Activations Density 0.084%