INDEX

Explanations

general statements about people

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

 gedachten

-1.77

ಞ

-1.71

 groet

-1.71

栗

-1.70

꯷

-1.68

 洗面

-1.64



-1.62

ssohn

-1.61

 minta

-1.61

毟

-1.60

POSITIVE LOGITS

</h3>

2.06

1.94

}`}>

1.84

全世界

1.81

国外

1.72

в

1.72

 ")");

1.70

 wenige

1.69

things

1.66

帖子

1.65

Activations Density 0.021%