INDEX

Explanations

mentions of specific names

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

 mothers

-0.10

 Mothers

-0.10

 mate

-0.10

 himself

-0.10

å¤§å®¶

-0.10

 fleets

-0.09

 collabor

-0.09

 author

-0.09

 dude

-0.09

 granddaughter

-0.09

POSITIVE LOGITS

duo

0.42

two

0.36

äºĮäºº

0.32

ä¸¤ä¸ª

0.32

 pair

0.31

two

0.29

ä¸¤äºº

0.28

Duo

0.27

Two

0.26

Two

0.25

Activations Density 0.358%