INDEX

Explanations

latitude and longitude coordinates

The neuron activates on mentions of geographic coordinate terms—specifically “lat,” “lng,” “latitude,” or “longitude.”

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

 However

-1.95

-1.78

.");

-1.69

If

-1.66

麈

-1.65

to

-1.64

.’

-1.59

ญี่ป

-1.57

 They

-1.55

 With

-1.55

POSITIVE LOGITS

2.23

2.22

 técn

1.84

 pérd

1.84

 indiví

1.74

1.72

 rengi

1.70

``

1.68

both

1.66

 etek

1.60

Activations Density 0.007%