INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bracelet

-0.11

Aus

-0.11

kop

-0.11

erti

-0.10

jaw

-0.10

deen

-0.10

 parad

-0.10

 clue

-0.10

UDA

-0.10

UIS

-0.10

POSITIVE LOGITS

Rut

0.09

 segreg

0.09

 mutual

0.08

enge

0.08

Mor

0.07

 coke

0.07

 intermedi

0.07

 flip

0.07

vc

0.07

 bridges

0.07

Activations Density 0.000%

No Known Activations