INDEX

Explanations

documentation structure

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

at

-1.79

 with

-1.72

and

-1.57

has

-1.45

in

-1.41

at

-1.41

-1.40

may

-1.37

as

-1.33

 during

-1.33

POSITIVE LOGITS

 siè

1.40

ᕮ

1.31

gorra

1.28

 testé

1.27

$,

1.27

 superstar

1.26

ırl

1.26

íte

1.26

fører

1.25

 cukru

1.24

Activations Density 0.002%