INDEX

Explanations

terms related to political ideologies and movements

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

er

-0.10

nier

-0.07

smith

-0.07

ish

-0.07

bie

-0.07

sob

-0.07

least

-0.07

ist

-0.07

 Diaz

-0.06

sar

-0.06

POSITIVE LOGITS

otle

0.10

ically

0.09

ische

0.09

(ic

0.08

-leaning

0.08

udies

0.07

ries

0.07

isches

0.07

 Trap

0.07

ICO

0.07

Activations Density 0.073%