INDEX

Explanations

titles of books or articles

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

 когда

-1.32

 после

-1.30

When

-1.29

Because

-1.27

 when

-1.27

 vemos

-1.23

Very

-1.22

↵↵

-1.21

的时候

-1.18

 очень

-1.18

POSITIVE LOGITS

kiem

1.48

 that

1.48

 citroen

1.42

НЕ

1.39

 dorp

1.38

ſy

1.37

 incrí

1.36

 ſtre

1.34

 ſte

1.33

 ſta

1.32

Activations Density 0.065%