INDEX

Explanations

times, twice, tripled, more

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

1.91

in

1.77

ing

1.73

ü

1.71

iz

1.66

won

1.59

प

1.59

au

1.56

ut

1.49

os

1.49

POSITIVE LOGITS

Эта

1.53

ių

1.44

 tablecloth

1.42

িয়াম

1.40

আরো

1.38

 மடங்கு

1.38

 convolutions

1.35

 الأولى

1.33

 הג

1.32

ેલા

1.32

Activations Density 0.088%