INDEX

Explanations

roman numeral I followed by period

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

ppure

1.10

 podia

1.07

 jossa

1.05

<code>

0.97

 sedangkan

0.96

 pokok

0.95

ainkan

0.94

oltre

0.93

 uitvo

0.93

णुओं

0.93

POSITIVE LOGITS

】

2.51

）

2.51

2.43

》

2.43

』

2.38

2.33

2.27

！

2.26

的

2.23

也

2.22

Activations Density 0.104%