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

ula

-0.10

 Trom

-0.10

otech

-0.10

cw

-0.09

ober

-0.09

yro

-0.09

cio

-0.09

 inher

-0.09

aycast

-0.09

YRO

-0.09

POSITIVE LOGITS

ienne

0.09

 Jude

0.09

.lift

0.09

ijo

0.09

Hed

0.09

 reigning

0.09

 Hanson

0.09

 Rent

0.08

cle

0.08

ÑĥÑģÑĤ

0.08

Activations Density 0.000%

No Known Activations

This feature has no known activations.