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

undy

-0.09

 Sadd

-0.09

ibo

-0.09

 unthinkable

-0.09

undi

-0.09

 Sent

-0.09

 Mobil

-0.08

 unheard

-0.08

 SENT

-0.08

 Correction

-0.08

POSITIVE LOGITS

 hurdles

0.12

 guarding

0.10

 schem

0.10

 gate

0.10

 discour

0.10

 hoops

0.10

 Caval

0.10

 erected

0.10

 hoop

0.10

 carnival

0.10

Activations Density 0.000%

No Known Activations