INDEX

Explanations

technical documentation

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

Dermott

-1.04

This

-0.93

for

-0.92

ఏ

-0.88

inario

-0.86

For

-0.86

áticas

-0.85

طيع

-0.85

illé

-0.84

 jaundice

-0.84

POSITIVE LOGITS

σσ

1.03

 Amérique

0.99

 avesse

0.98

 también

0.97

是一個

0.95

 composés

0.95

 צו

0.95

 élas

0.94

ăți

0.94

eaza

0.94

Activations Density 0.077%