INDEX

Explanations

abstract concepts and psychological states

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fdPar

0.29

ujete

0.27

laublich

0.27

 regolare

0.27

 Elektrokhimiya

0.27

−</

0.26

ionalmente

0.26

łączyć

0.26

 contrôler

0.26

 rodean

0.25

POSITIVE LOGITS

з

0.26

 There

0.24

िक

0.22

 citizenry

0.22

getic

0.22

…

0.21

 нар

0.21

<start_of_image>

0.20

적이

0.20

ل

0.20

Activations Density 0.177%