INDEX

Explanations

punctuation followed by words

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

入って

-1.39

颦

-1.31

 Entdecken

-1.30

ГЛА

-1.25

曏

-1.25

 díky

-1.23

 Otras

-1.23

 Encuentra

-1.22

klád

-1.20

jalanan

-1.17

POSITIVE LOGITS

import

1.66

⫽

1.51

туру

1.38

ينات

1.30

↵

1.24

anted

1.23

1.22

Don

1.22

あぁ

1.20

cen

1.19

Activations Density 0.010%