INDEX

Explanations

conversational questions and statements

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

 imprint

-0.09

oog

-0.09

ittings

-0.09

 surv

-0.09

isia

-0.08

napshot

-0.08

folios

-0.08

 porad

-0.08

 Says

-0.08

Ã¼f

-0.08

POSITIVE LOGITS

 speaking

0.20

 Speaking

0.18

Speaking

0.18

Did

0.17

did

0.17

Did

0.15

 favorite

0.15

-speaking

0.15

 talking

0.14

favorite

0.14

Activations Density 0.161%