INDEX

Explanations

topic or subject

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

 specialties

-0.09

hazi

-0.09

(íģ¬ê¸°

-0.09

 emblem

-0.09

iasi

-0.09

Ð½Ð¾ÑĪ

-0.08

rouw

-0.08

akh

-0.08

ToLocal

-0.08

èĪĹ

-0.08

POSITIVE LOGITS

 topic

0.64

 subject

0.52

topic

0.46

 Topic

0.44

Topic

0.42

 theme

0.41

ä¸»é¢ĺ

0.38

subject

0.38

-topic

0.37

 topics

0.37

Activations Density 0.396%