INDEX

Explanations

assessing quality and status

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

惩

-1.40

mpagne

-1.27

绺

-1.26

 provocó

-1.24

 kutumia

-1.23

🐾

-1.23

savage

-1.23

 itself

-1.22

 bawat

-1.22

イング

-1.21

POSITIVE LOGITS

</em>

1.66

1.53

ถ้า

1.48

']

1.41

What

1.40

Глава

1.39

Статья

1.38

这

1.37

Что

1.37

无比

1.34

Activations Density 0.049%