INDEX

Explanations

quantifying land and distance

The neuron detects mentions of measured sizes, especially numeric area measurements (e.g. “X-acre”) 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

Ꭴ

-1.56

 gesteld

-1.45

 acompañada

-1.43

kosť

-1.42

 regelmäßig

-1.41

Concepto

-1.40

 Frequently

-1.34

ョン

-1.30

ﺰ

-1.27

ִים

-1.26

POSITIVE LOGITS

of

2.08

1.69

 achten

1.58

："

1.56

:'

1.52

 consejos

1.48

('

1.47

1.46

Activations Density 0.018%