INDEX

Explanations

in a text editor

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

ADIO

-0.10

unread

-0.09

obao

-0.09

 unread

-0.09

 Wald

-0.09

 Leonard

-0.09

hlen

-0.09

Wig

-0.09

deg

-0.08

deg

-0.08

POSITIVE LOGITS

 editor

0.34

 Editor

0.27

 edit

0.27

 editors

0.26

 editing

0.25

ç¼ĸè¾ĳ

0.25

Editor

0.25

editor

0.24

edit

0.24

 Edit

0.23

Activations Density 0.047%