INDEX

Explanations

conversational greetings

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

ardi

-0.10

è®¸

-0.09

owl

-0.09

 opportun

-0.09

ï¾Į

-0.08

MainMenu

-0.08

ilion

-0.08

 consecutive

-0.08

arti

-0.08

 conta

-0.08

POSITIVE LOGITS

atus

0.10

ATUS

0.10

anut

0.09

åĳĢ

0.09

ghest

0.09

acerb

0.09

bole

0.09

 there

0.09

 welcome

0.09

/welcome

0.08

Activations Density 0.087%