INDEX

Explanations

seeds, data, cut, wire, glass, Fashion, kidney, spin, American, justice, substrate, Delta

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

 hanem

-1.45

lasyon

-1.40

احبه

-1.35

lamó

-1.27

jení

-1.26

蔣

-1.23

éről

-1.20

 Drž

-1.20

 brengen

-1.17

 escova

-1.17

POSITIVE LOGITS

of

1.90

for

1.49

1.40

is

1.39

 into

1.25

we

1.18

 principalement

1.16

1.15

 eden

1.14

still

1.13

Activations Density 0.140%