INDEX

Explanations

criminal accomplice

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

 harassing

-0.86

kräfte

-0.86

 réussi

-0.84

 représentent

-0.80

Opponent

-0.77

カラフル

-0.77

 considerate

-0.75

 pourront

-0.74

 įva

-0.73

 Integrating

-0.72

POSITIVE LOGITS

 accomplice

2.53

 aiding

2.16

 comp

2.05

 accomp

1.96

 participation

1.88

 assisting

1.81

 accessory

1.79

 participate

1.77

 participated

1.73

参与

1.73

Activations Density 0.043%