INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

Started

0.61

ট

0.59

People

0.56

Till

0.55

에

0.55

Tesla

0.54

Stranger

0.54

 школи

0.54

Talking

0.53

’

0.53

POSITIVE LOGITS

 kinds

0.59

 vínculo

0.59

 inept

0.57

 kimono

0.55

 indetermin

0.54

 саны

0.54

 embodied

0.53

 inadvert

0.53

 exterior

0.53

 измене

0.52

Activations Density 0.000%

No Known Activations