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

Wel

-0.11

wel

-0.10

/tutorial

-0.09

Wel

-0.09

iets

-0.09

 fren

-0.09

 Notre

-0.09

XM

-0.08

Scoped

-0.08

ÅĻ

-0.08

POSITIVE LOGITS

Brad

0.10

afia

0.10

Raf

0.10

iew

0.09

 æµ

0.09

 eliminating

0.09

Tyr

0.08

punk

0.08

elig

0.08

 progressive

0.08

Activations Density 0.000%

No Known Activations