INDEX

Explanations

çļĦéħį, éľĢè´Ń, å·¥ç¨ĭä¸į

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

gi

-0.10

ayo

-0.10

aney

-0.10

éĥ¡

-0.10

 bounce

-0.09

Äħ

-0.09

 Taipei

-0.09

 Nguyen

-0.09

 Tran

-0.09

 Jing

-0.09

POSITIVE LOGITS

 publicity

0.12

 Suggestions

0.10

 nucle

0.10

Rao

0.10

 propaganda

0.10

 Comprehensive

0.09

éĹ

0.09

 Epid

0.09

 handsome

0.09

Activations Density 0.194%