INDEX

Explanations

Belgian

The neuron detects mentions of Belgium or Belgian‐related geographic/national terms (e.g. “Belgian,” names of Belgian provinces, clubs, etc.).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

Our

-1.87

 from

-1.86

 With

-1.79

 Some

-1.77

 here

-1.70

 Here

-1.69

 This

-1.67

our

-1.66

 this

-1.63

and

-1.59

POSITIVE LOGITS

Qualität

1.58

 correos

1.54

 FOLLOWING

1.49

鋱

1.49

++++++++++++++++

1.48

футболка

1.47

Brisbane

1.46

ѭ

1.45

 passos

1.44

 バッジ

1.43

Activations Density 0.044%