INDEX

Explanations

improve performance and quality

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

inel

-0.11

imity

-0.10

 Attendance

-0.09

Fry

-0.09

 alto

-0.08

alty

-0.08

USAGE

-0.08

noÅĽci

-0.08

ply

-0.08

antha

-0.08

POSITIVE LOGITS

 performance

0.38

performance

0.30

 performances

0.29

æĢ§èĥ½

0.29

 Performance

0.28

Performance

0.26

-performance

0.22

 performan

0.22

.performance

0.22

 speed

0.21

Activations Density 0.050%