INDEX

Explanations

FileCheck

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

 miliar

-0.93

ΟΥ

-0.92

}&

-0.88

神的

-0.88

 suspect

-0.87

three

-0.86

 щодо

-0.85

crackers

-0.85

 will

-0.85

 комнаты

-0.85

POSITIVE LOGITS

 that

1.20

 putem

1.03

 muebles

0.98

 granja

0.98

 '=',

0.96

 aktivitas

0.94

slowly

0.94

 voed

0.93

 horarios

0.92

 preços

0.91

Activations Density 0.001%