INDEX

Explanations

relative or compared quantities

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

 sortable

-0.10

ãģłãģĳãģ§

-0.10

-0.09

RefCount

-0.08

illed

-0.08

 createdBy

-0.08

 pros

-0.08

fkk

-0.08

indi

-0.08

POSITIVE LOGITS

 compared

0.80

 Compared

0.58

 relative

0.47

relative

0.35

æ¯Ķ

0.35

 Relative

0.34

 compare

0.32

pared

0.32

comp

0.31

Relative

0.29

Activations Density 0.124%