INDEX

Explanations

Southern Poverty Law Center

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 северо

0.50

북

0.46

ಸ್ಟ್

0.41

collapse

0.39

すごく

0.38

 undergo

0.38

北

0.37

 synerg

0.37

്യം

0.37

 sentença

0.37

POSITIVE LOGITS

Southern

0.52

 Southern

0.51

wark

0.47

UTHERN

0.46

 Sudanese

0.45

downs

0.44

絮

0.42

South

0.42

 African

0.40

African

0.38

Activations Density 0.007%