INDEX

Explanations

just a normal or about to

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

shy

-0.09

bsites

-0.09

à¸ģà¸³à¸¥

-0.09

ÄįasÃŃ

-0.09

Ñĵ

-0.09

 addCriterion

-0.08

ibase

-0.08

ï¸

-0.08

rut

-0.08

POSITIVE LOGITS

 average

0.15

ifi

0.14

iciar

0.13

 plain

0.13

 generic

0.13

 Average

0.13

 generally

0.12

Average

0.12

 normal

0.12

æĻ®éĢļ

0.12

Activations Density 0.024%