INDEX

Explanations

can see donkeys

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

 travel

-0.11

 Skate

-0.11

 camping

-0.11

 Camping

-0.11

 Vacation

-0.11

 nghá»ī

-0.11

travel

-0.10

 vacation

-0.10

æĹħ

-0.10

 skiing

-0.10

POSITIVE LOGITS

 horse

0.15

 guided

0.15

 Guid

0.14

guided

0.13

zip

0.13

Guid

0.13

Kay

0.12

seg

0.12

Seg

0.12

 paras

0.12

Activations Density 0.043%