INDEX

Explanations

Magdalene, Marianne, Kanza

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

 himself

-0.12

 handsome

-0.12

 Jana

-0.12

Cra

-0.12

Muj

-0.10

 Clara

-0.10

ÑĥÑİÑīÐ¸Ð¹

-0.10

 Lola

-0.09

 Himself

-0.09

yers

-0.09

POSITIVE LOGITS

 herself

0.18

ina

0.16

ricia

0.14

atrice

0.14

entina

0.14

 Thá»ĭ

0.13

ita

0.12

her

0.12

istine

0.12

edith

0.12

Activations Density 0.138%