INDEX

Explanations

top lists and rankings

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

 neque

-1.09

frequencies

-0.95

 usize

-0.94

 entirety

-0.91

enservice

-0.89

two

-0.88

 bloem

-0.88

 aang

-0.85

лкой

-0.84

 crédit

-0.83

POSITIVE LOGITS

 worst

1.34

 memorable

1.34

 famous

1.26

 weird

1.20

Notable

1.16

worst

1.16

だと思う

1.14

unusual

1.14

 foods

1.13

 celebrity

1.13

Activations Density 0.121%