INDEX

Explanations

yep, y, or ey followed by common words

Y or y followed by certain characters

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ार्थ

0.76

ില്ല

0.69

ार

0.65

ानुसार

0.64

ിൽ

0.60

ുകൊ

0.60

ान्

0.59

ानि

0.59

ുകൊണ്ട്

0.59

ाम

0.58

POSITIVE LOGITS

outube

1.19

yyyy

1.13

yyyyyyyy

1.08

ுள்ளனர்

1.02

ுள்ளார்

1.00

yy

0.93

oung

0.91

ுள்ள

0.85

vonne

0.83

ுள்ளது

0.82

Activations Density 0.408%