INDEX

Explanations

references to historical events and attacks

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

ÑĪÐ¸Ð±

-0.07

reg

-0.07

ourg

-0.06

egan

-0.06

esen

-0.06

thren

-0.06

aby

-0.06

VML

-0.06

į°

-0.06

POSITIVE LOGITS

 McCart

0.07

inal

0.07

hij

0.06

 Liberties

0.06

 tjejer

0.06

rust

0.06

inn

0.06

Î¼Î¹

0.06

 lesbische

0.06

zf

0.06

Activations Density 0.001%