INDEX

Explanations

UMAP Uniform Manifold Approximation

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

 åį

-0.10

bil

-0.09

 vent

-0.09

DeV

-0.09

ully

-0.09

 Psychic

-0.09

 apex

-0.09

 junk

-0.09

uhan

-0.09

aign

-0.09

POSITIVE LOGITS

dbs

0.14

ag

0.14

DB

0.14

 density

0.14

Vor

0.13

ç°

0.12

 Noise

0.12

 linkage

0.12

 noise

0.12

å¯Ĩ

0.12

Activations Density 0.018%