INDEX

Explanations

feminine pronouns in multiple languages

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

 denen

-0.15

 ÐºÐ¾ÑĤÐ¾ÑĢÐ¾Ð¼

-0.14

 celui

-0.13

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐ¼

-0.13

izados

-0.12

 ÑıÐºÐ¾Ð¼Ñĥ

-0.12

_globals

-0.11

 quello

-0.11

primir

-0.11

 kterÃ©m

-0.10

POSITIVE LOGITS

å¥¹

0.38

she

0.38

 Ð¾Ð½Ð°

0.35

 ella

0.33

 haar

0.33

her

0.33

ela

0.32

 Ð½ÐµÐµ

0.31

ÙĩØ§

0.30

she

0.30

Activations Density 0.240%