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

 Marcus

-0.08

onor

-0.08

 emph

-0.08

 fading

-0.07

 Herman

-0.07

 Morrison

-0.07

olas

-0.07

 moot

-0.07

ament

-0.07

/rem

-0.07

POSITIVE LOGITS

FE

0.11

linger

0.11

FE

0.11

osten

0.10

oci

0.10

abbo

0.10

 tween

0.10

 gains

0.10

almart

0.10

arro

0.10

Activations Density 0.000%

No Known Activations