INDEX

Explanations

greetings and technical terms

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

੍ਹ

2.56

дцать

2.51

ED

2.43

𝚒

2.32

 retrograde

2.29

רה

2.23

υ

2.21

ๆ

2.18

్రో

2.14

উন্ট

2.14

POSITIVE LOGITS

 szok

2.95

র্মে

2.71

 zewnętrzne

2.64

žal

2.59

indungi

2.59

荟

2.48

 sareng

2.46

 ذہ

2.45

bolinks

2.45

gur

2.44

Activations Density 0.002%