INDEX

Explanations

World War II Japanese internment

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

abo

-0.12

ayi

-0.10

 chast

-0.10

 Kaplan

-0.09

 paddle

-0.09

 æ¯

-0.09

addle

-0.09

DIN

-0.08

Beam

-0.08

otre

-0.08

POSITIVE LOGITS

 intern

0.23

 Intern

0.19

Intern

0.18

intern

0.17

 camps

0.15

 Enemy

0.15

 enemy

0.15

enemy

0.14

 Japanese

0.14

Japanese

0.13

Activations Density 0.013%