INDEX

Explanations

Proper nouns/place names

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hora

-1.17

 оригіналу

-0.68

 hora

-0.66

andy

-0.66

♭

-0.63

 oprot

-0.57

Hora

-0.53

timewa

-0.51

'{@

-0.51

 Hora

-0.50

POSITIVE LOGITS

 scolaires

0.76

 sécher

0.69

 colorés

0.69

Tembelea

0.68

 normaux

0.68

 giapp

0.66

 automatiques

0.66

 paroisse

0.65

 TestCase

0.65

 carreaux

0.65

Activations Density 1.541%