INDEX

Explanations

glasses and sunglasses

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

Ã¼m

-0.10

iko

-0.09

.vertx

-0.09

 Velvet

-0.09

abl

-0.08

krom

-0.08

antha

-0.08

 Sanctuary

-0.08

 -*-č\n

-0.08

 Stub

-0.08

POSITIVE LOGITS

 glasses

0.28

 goggles

0.24

eye

0.24

 Glasses

0.23

ey

0.22

Eye

0.21

Eye

0.18

 spect

0.18

oggles

0.17

-eye

0.16

Activations Density 0.001%