INDEX

Explanations

highly flexible customizable scalable

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

 adaptable

-0.13

unl

-0.10

SENS

-0.09

ibri

-0.09

ynos

-0.09

 Jensen

-0.08

ellig

-0.08

ysa

-0.08

 NEGLIGENCE

-0.08

POSITIVE LOGITS

ext

0.22

 flex

0.17

flex

0.17

 flexible

0.17

-flex

0.16

 flexibility

0.15

rob

0.15

çģµ

0.15

Rob

0.14

 robust

0.14

Activations Density 0.083%