INDEX

Explanations

ListViews and UI proxies

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

 发型

-1.52

↵↵↵

-1.41

↵↵↵↵↵↵↵↵↵↵

-1.34

 ewigen

-1.29

↵↵↵↵

-1.29

beiter

-1.28

↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.25

NAR

-1.25

Ϻ

-1.24

thulhu

-1.23

POSITIVE LOGITS

We

1.67

 dwóch

1.45

>--}}

1.41

å

1.36

当下

1.31

Напомним

1.30

テーション

1.30

 travail

1.28

 precisar

1.27

 ogó

1.26

Activations Density 0.011%