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

Ã³r

-0.08

 Loren

-0.08

 Stan

-0.08

 Priv

-0.08

 Sheldon

-0.08

 Cent

-0.08

iled

-0.08

zp

-0.08

 floated

-0.08

-0.07

POSITIVE LOGITS

 unavoidable

0.10

 unwilling

0.10

 carousel

0.10

 contingent

0.10

 leftover

0.09

 candles

0.09

 collaps

0.09

clas

0.09

 couples

0.09

oft

0.09

Activations Density 0.000%

No Known Activations