INDEX

Explanations

No Explanations Found

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

⇒

1.03

 autorità

1.00

是个

0.97

在

0.94

ępuje

0.91

tg

0.90

étés

0.90

ln

0.89

ంటర్

0.88

આ

0.86

POSITIVE LOGITS

 arguably

1.93

 admittedly

1.91

 albeit

1.83

perhaps

1.81

 perhaps

1.77

 presumably

1.77

albeit

1.75

 certes

1.74

presumably

1.70

 literalmente

1.69

Activations Density 0.266%

No Known Activations