INDEX

Explanations

multilingual text and punctuation

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

 cushioning

1.50

𝐫

1.46

𝑟

1.42

𝐞

1.40

 creases

1.38

denominator

1.36

 endure

1.35

 durability

1.34

след

1.33

 discontinuities

1.30

POSITIVE LOGITS

моль

1.44

ittäin

1.42

ikiem

1.33

ી

1.31

 stanie

1.27

ześ

1.26

ਸ਼

1.24

ﻉ

1.20

ánto

1.20

кара

1.19

Activations Density 0.128%