INDEX

Explanations

trusted entities or connections

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

 Rosa

-0.11

_JS

-0.11

arness

-0.10

arching

-0.09

Gaw

-0.08

 Danh

-0.08

ITIES

-0.08

à¸ĵ

-0.08

avit

-0.08

POSITIVE LOGITS

 adults

0.14

/lic

0.14

 source

0.14

worth

0.13

 individuals

0.12

 sources

0.11

edo

0.11

 friend

0.11

 adult

0.11

/app

0.11

Activations Density 0.012%