INDEX

Explanations

Unlike X, Y

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

-0.11

ools

-0.10

 jakÃ©

-0.09

æĺ¯ä»Ģä¹Ī

-0.09

 nÃło

-0.09

 Loren

-0.08

 Lambert

-0.08

eneg

-0.08

 gÃ¬

-0.08

 ÑĤÐ¾Ð±ÑĤÐ¾

-0.08

POSITIVE LOGITS

 which

0.37

 whose

0.37

which

0.34

whose

0.30

who

0.26

 vá»ĳn

0.25

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐ¹

0.24

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐµ

0.23

 ÐºÐ¾ÑĤÐ¾ÑĢÐ°Ñı

0.22

 ktÃ³ry

0.22

Activations Density 0.275%