INDEX

Explanations

names and roles of historical figures

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omik

-0.07

éĸ

-0.06

oya

-0.06

 ÙħÙĨØ¸

-0.06

appings

-0.06

 ÑģÐ¾Ð±

-0.06

onus

-0.06

INES

-0.06

Ð±Ð¾Ð¼

-0.06

Dew

-0.06

POSITIVE LOGITS

 Authentic

0.08

 auth

0.07

 authenticity

0.07

auth

0.07

 authentic

0.07

Auth

0.07

 uniforms

0.07

reen

0.07

 reconstructed

0.07

 cosplay

0.07

Activations Density 0.011%