INDEX

Explanations

english language in html

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

ımda

-1.74

 become

-1.37

-1.36

 agujas

-1.36

 Vögel

-1.36

 також

-1.34

 sentía

-1.33

pisah

-1.31

Пер

-1.30

觚

-1.30

POSITIVE LOGITS

of

2.13

 inim

1.65

])){

1.52

dfrac

1.52

一群

1.46

 ярма

1.46

Ⴀ

1.46

строи

1.42

1.38

1.36

Activations Density 0.011%