INDEX

Explanations

locations and distribution

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

ìŀĲìĿ¸

-0.09

 universally

-0.09

ensburg

-0.09

ween

-0.09

 unanimous

-0.09

[[]

-0.08

 Overse

-0.08

leans

-0.08

rys

-0.08

aticon

-0.08

POSITIVE LOGITS

 throughout

0.43

 across

0.40

 Throughout

0.29

 Across

0.26

Throughout

0.24

Across

0.23

acc

0.16

 coast

0.14

 around

0.14

 ìłĦêµŃ

0.13

Activations Density 0.107%