INDEX

Explanations

stood opposite

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

 hitting

-0.10

 Rena

-0.09

.cg

-0.09

.spotify

-0.08

icopt

-0.08

occo

-0.08

WidgetItem

-0.08

åľŃ

-0.08

 asleep

-0.08

inters

-0.08

POSITIVE LOGITS

 face

0.36

éĿ¢

0.25

face

0.25

 Face

0.22

.face

0.21

(face

0.20

-face

0.20

 facing

0.19

 encounter

0.19

 faced

0.19

Activations Density 0.104%