INDEX

Explanations

places and regions

The neuron is triggered by numeric expressions—digits, measurements, years, and other numbers in the text.

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

 medlem

-1.33

 regeringen

-1.33

again

-1.33

 hunne

-1.31

 ラック

-1.27

strukturen

-1.23

 zijne

-1.23

ﮨ

-1.22

之类的

-1.22

DÉ

-1.22

POSITIVE LOGITS

 this

1.55

 these

1.47

it

1.30

MeasureSpec

1.20

any

1.17

昕

1.16

ribusiness

1.16

であり

1.13

 Neuen

1.13

 each

1.10

Activations Density 0.111%