INDEX

Explanations

property floor levels

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

 eenvou

-1.32

 Однако

-1.30

 alterações

-1.23

or

-1.21

 różnych

-1.20

 einfache

-1.20

也只能

-1.19

 falsch

-1.18

もありますが

-1.17

がこの

-1.16

POSITIVE LOGITS

摃

1.36

 haja

1.30

忪

1.25

1.23

LEIA

1.16

风的

1.16

")"

1.15

uples

1.13

 your

1.12

Activations Density 0.008%