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

 Crow

-0.10

Crow

-0.09

-for

-0.08

-on

-0.08

 triple

-0.08

 Graves

-0.08

Bol

-0.08

 moments

-0.08

 elong

-0.08

ved

-0.08

POSITIVE LOGITS

 Vict

0.11

 lurking

0.10

Arb

0.10

áºŃ

0.09

stu

0.09

 tens

0.09

 Naughty

0.09

 creeping

0.09

wagon

0.09

 Cath

0.09

Activations Density 0.000%

No Known Activations