INDEX

Explanations

who proposed or is known for work

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

 devis

-0.12

 pioneered

-0.11

Kaw

-0.09

 reconstruct

-0.09

æ²

-0.09

âĢŀP

-0.09

 complic

-0.08

Wak

-0.08

URN

-0.08

POSITIVE LOGITS

 discover

0.15

 publish

0.15

 discovery

0.15

åıĳçİ°

0.14

 study

0.14

 discovered

0.14

 work

0.13

 discovering

0.13

 popular

0.13

 redis

0.13

Activations Density 0.109%