INDEX

Explanations

li, lis, lix, lich, lian, lic

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

wald

-0.10

 bear

-0.10

 Bear

-0.10

uco

-0.10

led

-0.10

lement

-0.09

ained

-0.09

es

-0.09

LC

-0.09

 Ashe

-0.09

POSITIVE LOGITS

utenant

0.12

chten

0.11

ITLE

0.11

erce

0.11

entious

0.10

enci

0.10

finity

0.10

 vá»±c

0.10

RARY

0.10

ÐµÐ½Ð·

0.10

Activations Density 0.045%