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

stringLiteral

-0.11

onde

-0.10

aturas

-0.10

âĢ¦↵↵↵↵

-0.10

agi

-0.10

NX

-0.10

zon

-0.10

IFn

-0.09

DonaldTrump

-0.09

_OW

-0.09

POSITIVE LOGITS

Mi

0.09

adh

0.08

Mi

0.08

 SPEC

0.08

ros

0.08

 specifying

0.08

committed

0.08

 able

0.08

Gin

0.08

 Boys

0.08

Activations Density 0.000%

No Known Activations