INDEX

Explanations

expenses or spending

This neuron detects mentions of paying money to cover costs or bills.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

}})^{

0.62

 ቅር

0.59

ច្រ

0.58

विषयी

0.57

មើ

0.57

heast

0.56

oruč

0.55

status

0.54

victory

0.54

acter

0.54

POSITIVE LOGITS

 expenses

2.30

expenses

1.98

 Expenses

1.87

 gastos

1.85

Expenses

1.80

 расходы

1.73

 spese

1.68

 purchases

1.65

 expenditures

1.64

 dépenses

1.61

Activations Density 0.869%