INDEX

Explanations

describing facial movements

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

 hairs

-0.09

 horns

-0.09

HBO

-0.09

 tactile

-0.09

ubl

-0.09

 ears

-0.08

Wyn

-0.08

 Hair

-0.08

 Gain

-0.08

 Tamb

-0.08

POSITIVE LOGITS

 motion

0.20

kin

0.17

 gesture

0.17

 movement

0.16

 Motion

0.15

gesture

0.15

Motion

0.14

 Movement

0.14

 Gesture

0.14

motion

0.13

Activations Density 0.094%