INDEX

Explanations

Toyota, automakers, Nissan, Honda

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

 Kawasaki

-0.12

 Jaguar

-0.10

 Manit

-0.10

 ä¸¶

-0.10

.gg

-0.09

 Khan

-0.09

 æ©

-0.09

elage

-0.09

 Kashmir

-0.09

 Cadillac

-0.09

POSITIVE LOGITS

 Toyota

0.25

Toyota

0.21

Toy

0.19

Pri

0.18

Toy

0.16

Pri

0.15

 Lexus

0.15

toy

0.14

 Levin

0.14

toy

0.13

Activations Density 0.021%