INDEX

Explanations

initials followed by period

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

you

-1.37

both

-1.36

 vekt

-1.34

what

-1.32

🅖

-1.31

 beider

-1.30

-1.29

ср

-1.26

your

-1.23

itées

-1.23

POSITIVE LOGITS

æt

1.28

1.20

 kteří

1.16

국의

1.13

tyimages

1.12

 absence

1.10

 sièges

1.09

лены

1.09

Terre

1.08

例句

1.07

Activations Density 0.084%