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

itag

-0.11

 abundant

-0.10

arily

-0.09

ationally

-0.09

anse

-0.09

eed

-0.09

tb

-0.09

ially

-0.09

plat

-0.09

 Serge

-0.09

POSITIVE LOGITS

gap

0.10

 distortion

0.09

lcd

0.09

-confirm

0.08

 Samar

0.08

gap

0.08

oling

0.08

enko

0.08

vor

0.08

roman

0.08

Activations Density 0.000%

No Known Activations