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

 spit

-0.11

 mono

-0.09

Extend

-0.09

 Extend

-0.09

 Govern

-0.08

 interchange

-0.08

Inactive

-0.08

raq

-0.08

BO

-0.08

pred

-0.08

POSITIVE LOGITS

 Dire

0.12

atta

0.11

NIC

0.10

 loos

0.10

atte

0.10

pen

0.10

-san

0.10

-publish

0.10

 sidel

0.10

deg

0.09

Activations Density 0.000%

No Known Activations