INDEX

Explanations

operators and programming constructs

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

ãģ¨ãģĵãĤį

-0.14

erner

-0.10

ãģ¨ãģį

-0.10

abl

-0.10

naires

-0.09

ee

-0.09

BuilderInterface

-0.09

ABLE

-0.09

ebi

-0.09

eners

-0.09

POSITIVE LOGITS

ship

0.23

ial

0.22

ials

0.20

ially

0.20

ate

0.16

hip

0.16

ily

0.15

iale

0.14

azzi

0.14

stvo

0.13

Activations Density 0.153%