INDEX

Explanations

sets apart or distinguishes

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

 dispos

-0.11

 importance

-0.09

cor

-0.09

Wh

-0.09

 contrasting

-0.09

 stran

-0.09

 Equals

-0.09

alion

-0.09

YT

-0.09

 surrounding

-0.08

POSITIVE LOGITS

 Unique

0.21

 Ð¾ÑĤÐ»Ð¸Ñĩ

0.21

 distingu

0.20

åĮº

0.19

 sets

0.19

 diferencia

0.19

 stands

0.19

Unique

0.19

 unique

0.18

 uniqueness

0.18

Activations Density 0.081%