INDEX

Explanations

improve skin appearance

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

stasy

-0.09

thon

-0.09

uci

-0.09

å¸¯

-0.09

Toolkit

-0.09

à¸£à¸¡

-0.09

debit

-0.09

 informat

-0.09

 shampoo

-0.09

sty

-0.08

POSITIVE LOGITS

 youth

0.20

 firm

0.19

sag

0.19

wr

0.18

der

0.18

 Coll

0.17

 Youth

0.17

pl

0.17

reg

0.16

firm

0.16

Activations Density 0.027%