INDEX

Explanations

interested in learning about

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

 certain

-0.11

 oneself

-0.10

 anymore

-0.10

-0.09

:/

-0.09

etti

-0.08

 Certain

-0.08

ey

-0.08

:|

-0.08

oret

-0.08

POSITIVE LOGITS

 nhÃ©

0.13

ä¼Ł

0.10

æ£Ĵ

0.10

 awesome

0.10

awesome

0.09

 exciting

0.09

åĲ§

0.09

âĶĲ

0.09

 strr

0.09

Ð¼Ð¾ÑĤ

0.08

Activations Density 0.110%