INDEX

Explanations

various things

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

à¹Ħà¸«à¸Ļ

-0.10

ubit

-0.09

alen

-0.08

cki

-0.08

iesen

-0.08

 Cham

-0.08

è¥

-0.08

 Mehr

-0.07

 neutr

-0.07

inator

-0.07

POSITIVE LOGITS

 things

0.79

 Things

0.61

things

0.57

Things

0.57

 cosas

0.50

 thing

0.46

 Ð²ÐµÑī

0.41

 vÄĽci

0.37

 choses

0.33

thing

0.31

Activations Density 0.098%