INDEX

Explanations

Words and coding

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

noun

-0.73

tvguidetime

-0.65

 noun

-0.58

verwijspagina

-0.53

 Rosenberg

-0.52

 Cruz

-0.51

and

-0.50

Noun

-0.48

of

-0.47

に入った

-0.45

POSITIVE LOGITS

 purpoſe

1.13

 itſelf

1.13

 Monfieur

1.08

 myſelf

1.07

 ſtate

1.04

 pleaſure

1.04

 faſt

1.02

 ſtand

1.01

 ſeveral

1.00

ſelves

0.98

Activations Density 2.106%