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

 Criterion

-0.12

 conceptual

-0.10

 Grain

-0.09

Criterion

-0.09

 Sext

-0.09

 indebted

-0.09

fc

-0.09

ansom

-0.09

wo

-0.09

 undis

-0.09

POSITIVE LOGITS

leon

0.10

maj

0.09

 Stap

0.08

tec

0.08

lug

0.08

 lick

0.08

ceu

0.08

sou

0.08

earing

0.08

kos

0.08

Activations Density 0.000%

No Known Activations

This feature has no known activations.