INDEX

Explanations

entities linked by conjunctions or separators

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

 یا

-1.19

或

-1.19

ignment

-1.16

だよ

-1.16

 или

-1.14

 dicono

-1.11

or

-1.09

konos

-1.08

prone

-1.05

 oder

-1.02

POSITIVE LOGITS

and

1.88

与

1.60

與

1.57

}-\

1.47

"-"

1.40

]-[

1.35

vs

1.34

 plus

1.34

'-'

1.32

 versus

1.31

Activations Density 0.324%