INDEX

Explanations

tasks like image recognition

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

UME

-0.11

æ²Ł

-0.09

çĲ´

-0.09

 cust

-0.09

 Carly

-0.09

visualization

-0.08

PLEX

-0.08

 mapped

-0.08

(SP

-0.08

 pinpoint

-0.08

POSITIVE LOGITS

 vision

0.27

 Vision

0.25

Vision

0.20

 recognition

0.20

 Recognition

0.20

vision

0.19

 Image

0.18

 object

0.18

 image

0.17

Recognition

0.17

Activations Density 0.107%