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

igs

-0.12

-0.11

Om

-0.09

 immersion

-0.09

 plunge

-0.09

DDL

-0.09

 pinned

-0.09

Cel

-0.09

 Atkins

-0.09

 CONSTANT

-0.09

POSITIVE LOGITS

quoi

0.10

oley

0.10

issen

0.09

 lobby

0.09

ker

0.09

eah

0.08

loon

0.08

 ration

0.08

worth

0.08

HC

0.08

Activations Density 0.000%

No Known Activations