INDEX

Explanations

summary or overview of topics

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

 acoged

-1.26

 logra

-1.01

 servire

-0.99

慤

-0.96

 Substanz

-0.94

 muere

-0.94

喟

-0.93

 herida

-0.93

實

-0.92

是一種

-0.92

POSITIVE LOGITS

of

5.63

 των

1.59

ของ

1.45

how

1.33

 dagens

1.23

 các

1.20

 ofthe

1.19

 vienas

1.16

 של

1.16

ником

1.15

Activations Density 0.130%