INDEX

Explanations

copyright and modify

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

 店舗

-0.86

пресс

-0.84

 liberals

-0.84

 footballers

-0.81

Bex

-0.81

 diseñ

-0.79

 Liberals

-0.79

 comforter

-0.79

 няма

-0.78

gelopen

-0.77

POSITIVE LOGITS

 Barry

0.81

 Арме

0.77

 interfacial

0.74

Paragraph

0.70

 terras

0.69

 tiro

0.69

▪

0.68

 acum

0.68

Barry

0.67

 infect

0.67

Activations Density 0.009%