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

elm

-0.08

 curse

-0.07

 explic

-0.07

 Curse

-0.07

 **↵

-0.07

 Boyle

-0.07

 contexts

-0.06

via

-0.06

 Curt

-0.06

ccoli

-0.06

POSITIVE LOGITS

Bip

0.11

 drum

0.10

bou

0.10

utos

0.10

 Drum

0.10

cki

0.10

Startup

0.09

 fever

0.09

 tomato

0.09

 informed

0.09

Activations Density 0.000%

No Known Activations