INDEX

Explanations

fashion items and categories

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

 apparel

-0.18

 garments

-0.15

 Apparel

-0.15

 garment

-0.13

 attire

-0.12

 Shirt

-0.12

è¡£

-0.12

 clothing

-0.11

 Clothing

-0.11

 shirt

-0.11

POSITIVE LOGITS

men

0.26

 women

0.21

Men

0.18

 formal

0.18

 occasion

0.16

 Formal

0.16

Men

0.15

 Women

0.15

-men

0.15

 casual

0.14

Activations Density 0.097%