INDEX

Explanations

mathematical or software equality

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

厚

1.21

onaut

1.18

orne

1.17

 moat

1.15

otrich

1.15

ὄ

1.13

moor

1.12

absorption

1.11

gyz

1.11

 うち

1.11

POSITIVE LOGITS

ที่

1.44

 Bismillahirrah

1.41

 yang

1.36

 परमात्मा

1.35

אין

1.31

 একখানি

1.31

精心

1.30

 những

1.28

ڠ

1.26

ที่ไม่

1.25

Activations Density 0.253%