INDEX

Explanations

cost of care and borrowing

The neuron spots numeric “cost of” or “living cost” expressions—i.e. mentions of costs or cost‐of‐living figures.

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

 itinerario

-1.87

 広場

-1.77

۠

-1.72

 líquida

-1.68

 africano

-1.68

ڧ

-1.65

 bayar

-1.62

nefis

-1.62

%"),

-1.60

اسپ

-1.60

POSITIVE LOGITS

is

2.14

1.71

 essas

1.67

1.66

1.62

at

1.57

("

1.56

 queste

1.51

↵↵

1.50

1.48

Activations Density 0.006%