INDEX

Explanations

money laundering cases

The neuron activates on words and phrases that signal large-scale quantities or emphasize magnitude (e.g. “billions,” “numerous,” “quantity,” “possible,” “comparable”).

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

ׇ

-2.70

 блюдо

-2.16

 catholique

-1.98

 растение

-1.95

 Pfar

-1.95

ֺ

-1.92

 گیاه

-1.91

 τὰ

-1.76

 botanique

-1.72

 النبات

-1.69

POSITIVE LOGITS

ּוֹ

2.97

וּ

2.73

ִּ

2.44

ֶּ

2.39

ַּ

2.33

 бампер

2.27

וֹ

2.17

 السياس

1.98

ְּ

1.95

᾿

1.92

Activations Density 0.290%