INDEX

Explanations

listing numbers and items

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

 kedua

-0.83

 rade

-0.78

二日

-0.73

second

-0.70

 second

-0.69

 voltar

-0.69

juu

-0.68

んです

-0.68

 ketat

-0.67

rua

-0.66

POSITIVE LOGITS

 Seventeenth

0.96

ULES

0.90

 seventeenth

0.87

XVI

0.79

.}~\

0.79

 psychosocial

0.79

 процессов

0.78

กระ

0.74

Platforms

0.74

Ses

0.73

Activations Density 0.026%