INDEX

Explanations

qualities and characteristics

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

 zwar

-1.38

 этой

-1.36

and

-1.23

 этом

-1.15

 funkcji

-1.13

 savu

-1.10

 echter

-1.10

 viață

-1.06

 такие

-1.03

 asalto

-1.02

POSITIVE LOGITS

too

1.64

if

1.54

 тоже

1.47

1.34

 también

1.32

 نیز

1.30

 when

1.29

 also

1.28

it

1.26

 since

1.24

Activations Density 0.042%