INDEX

Explanations

work or professional experience

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

the

-2.97

鉭

-2.86

 améli

-2.83

mathrm

-2.81

-2.73

 ſaid

-2.70

孥

-2.70

},

-2.70



-2.67

気づ

-2.61

POSITIVE LOGITS

<bos>

3.50

↑↑↑</

3.05

vantaged

3.02

 einzel

3.00

ญี่ป

2.94

wiście

2.92

 größer

2.88

2.77

龟

2.70

龊

2.69

Activations Density 0.023%