INDEX

Explanations

express sexual orientation

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Axe

-0.10

lay

-0.10

Hud

-0.09

ï½¨

-0.09

 whites

-0.09

itta

-0.09

 èĩ

-0.08

riÃ¨re

-0.08

 Whites

-0.08

_SS

-0.08

POSITIVE LOGITS

 closet

0.17

 outing

0.16

 Coming

0.15

 acceptance

0.13

coming

0.13

Coming

0.13

 coming

0.13

 proud

0.13

 pride

0.13

åħ¬å¼Ģ

0.13

Activations Density 0.075%