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

 privately

-0.11

lf

-0.10

rire

-0.10

endi

-0.10

 whip

-0.10

cek

-0.10

 punct

-0.10

 nond

-0.10

Axe

-0.09

ocs

-0.09

POSITIVE LOGITS

 outweigh

0.09

pler

0.09

Vir

0.09

eken

0.09

 remed

0.08

Jou

0.08

Vir

0.08

VIR

0.08

arme

0.08

rat

0.08

Activations Density 0.000%

No Known Activations

This feature has no known activations.