INDEX

Explanations

group of people or entities

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

ä¸ĢåĢĭ

-0.12

ä¸Ģç§į

-0.12

 crews

-0.12

 pair

-0.11

 entire

-0.11

æĺ¯ä¸ª

-0.10

ä¸ĢäºĽ

-0.10

 flock

-0.10

 doubly

-0.09

 coppia

-0.09

POSITIVE LOGITS

 friends

0.13

 people

0.10

iesz

0.10

 individuals

0.10

 Friends

0.09

æľĭåıĭ

0.09

Friends

0.09

ren

0.09

tod

0.09

 merry

0.09

Activations Density 0.079%