INDEX

Explanations

organization names and descriptions

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

 Chew

-0.09

Hit

-0.09

_community

-0.09

 Federal

-0.09

 Sabb

-0.09

agem

-0.09

 Legend

-0.09

Cra

-0.09

 Donation

-0.09

æļ®

-0.08

POSITIVE LOGITS

 organization

0.23

 organizations

0.21

 groups

0.19

 organisation

0.19

 organisations

0.17

organization

0.17

 organizace

0.17

org

0.17

 Organizations

0.16

 Ð¾ÑĢÐ³Ð°Ð½Ð¸Ð·Ð°ÑĨÐ¸Ð¸

0.16

Activations Density 0.089%