INDEX

Explanations

punctuation and sentence endings

html/code delimiters

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 사람

0.68

 यही

0.51

 पहला

0.50

ポルト

0.46

簹

0.45

œuf

0.45

 प्रीपेड

0.45

ambh

0.44

】【

0.43

nung

0.43

POSITIVE LOGITS

↵↵

1.02

↵↵↵↵

0.86

↵↵↵↵↵

0.83

↵↵↵↵↵↵

0.74

↵↵↵

0.69

↵↵↵↵↵↵↵

0.67

↵↵↵↵↵↵↵↵↵↵↵

0.64

↵↵↵↵↵↵↵↵

0.63

↵↵↵↵↵↵↵↵↵↵↵↵↵

0.63

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.62

Activations Density 0.124%