INDEX

Explanations

code language suffixes

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

愜

-1.24

finanz

-1.20

 vaisselle

-1.17

 ถ้า

-1.13

 otras

-1.12

 если

-1.11

賔

-1.10

汽车

-1.09

amatkan

-1.09

ının

-1.09

POSITIVE LOGITS

↵

1.38

<em>

1.26

几位

1.16

}-

1.16

妩

1.15

 anyone

1.12

 şekilde

1.11

щая

1.10

igail

1.09

 realizando

1.09

Activations Density 0.049%