INDEX

Explanations

decorative items for display

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ִּ

-1.77

ּוֹ

-1.73

ֶּ

-1.61

ְּ

-1.52

ֵּ

-1.52

ַּ

-1.47

וּ

-1.27

 procedure

-1.19

niña

-1.18

berta

-1.16

POSITIVE LOGITS

ﻻ

1.48

 блюдо

1.45

ׇ

1.36

֩

1.29

 your

1.29

 сахара

1.27

 النبات

1.26

 chré

1.25

 trouve

1.22

 растение

1.22

Activations Density 0.024%