INDEX

Explanations

product designs and ideas

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

 Coat

-0.10

 Jeans

-0.10

 Craigslist

-0.09

AtIndex

-0.09

iese

-0.09

regon

-0.09

 Tinder

-0.09

 fertile

-0.08

å¥

-0.08

 Dress

-0.08

POSITIVE LOGITS

 designs

0.22

 Designs

0.18

 design

0.16

mug

0.15

_design

0.15

tees

0.15

TEE

0.15

tee

0.15

tee

0.14

 Design

0.14

Activations Density 0.048%