INDEX

Explanations

thing or things

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

åł´åĲĪãģ¯

-0.10

estro

-0.09

razil

-0.09

doch

-0.09

ãĤĪãģĨãģ§ãģĻ

-0.08

iller

-0.08

ëĿ¼ëıĦ

-0.08

ãģŁãĤģãģ«

-0.08

entieth

-0.08

å¥½çļĦ

-0.07

POSITIVE LOGITS

 thing

0.94

 things

0.81

thing

0.66

things

0.59

 Thing

0.57

 Things

0.56

 cosa

0.54

Thing

0.53

Things

0.53

 cosas

0.52

Activations Density 0.159%