INDEX

Explanations

lists of attributes

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

 demographic

-0.10

Ð¾Ð¶ÐµÑĤ

-0.09

 scenarios

-0.09

 Trab

-0.08

ilog

-0.08

qing

-0.08

 Astr

-0.08

 Dipl

-0.08

iyan

-0.08

izabeth

-0.08

POSITIVE LOGITS

 type

0.15

age

0.15

 degree

0.15

 amount

0.14

 size

0.12

 previous

0.11

age

0.11

 whether

0.11

amount

0.11

degree

0.11

Activations Density 0.057%