INDEX

Explanations

options in code configurations

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

鬭

-2.45

 Tonnen

-2.22

seamnă

-2.13

we

-2.11

 technically

-2.11

 zostały

-2.09

 vader

-2.08

 llegan

-2.06

使用

-2.03

 スケ

-2.02

POSITIVE LOGITS

༈

2.94

橚

2.73

เกง

2.44

癀

2.41

呖

2.39

Options

2.33

ครื่อง

2.33

嫫

2.31



2.31

 всѣ

2.25

Activations Density 0.005%