INDEX

Explanations

disabled per

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

’?

-1.43

’”

-1.30

鹩

-1.27

{$\

-1.24

 asin

-1.23

 вам

-1.22

geleitet

-1.18

ås

-1.18

."));

-1.17

peut

-1.16

POSITIVE LOGITS

 excessive

1.41

any

1.40

 change

1.37

 other

1.34

 several

1.29

 various

1.28

 numerous

1.25

 considerable

1.24

 difference

1.23

 large

1.22

Activations Density 0.057%