INDEX

Explanations

application

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

ardy

-0.10

$LANG

-0.09

agrant

-0.09

 Hardy

-0.09

agos

-0.09

Isl

-0.09

 Sherlock

-0.09

ifr

-0.09

beros

-0.09

 Applies

-0.09

POSITIVE LOGITS

 application

0.39

 applications

0.39

app

0.35

 apps

0.33

application

0.30

åºĶçĶ¨

0.29

applications

0.27

 Applications

0.26

 aplik

0.26

 á»©ng

0.25

Activations Density 0.220%