INDEX

Explanations

people, whom, or which

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

is

-1.95

 These

-1.39

 Thus

-1.37

has

-1.33

Use

-1.30

 если

-1.29

 розта

-1.28

Of

-1.25

 должна

-1.24

 About

-1.22

POSITIVE LOGITS

『

1.28

?''

1.20

''

1.16

物资

1.14

能在

1.14

 kater

1.14

hla

1.12

 fisk

1.10

ynı

1.10

Ś

1.10

Activations Density 0.047%