INDEX

Explanations

safe and helpful AI assistant

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

0.39

 Spaghetti

0.37

 Heavy

0.36

Wh

0.35

at

0.33

et

0.33

 Make

0.32

 Change

0.32

 Methods

0.32

 Melt

0.32

POSITIVE LOGITS

 conclus

0.32

деш

0.32

 droughts

0.32

ாண்ட

0.32

 approbation

0.31

 पांच

0.29

 cracks

0.28

 políticos

0.28

üren

0.28

 económicos

0.28

Activations Density 0.088%

No Known Activations