INDEX

Explanations

amount per unit of measure

The main thing this neuron does is detect numeric measurement expressions, especially values given as “number per unit (area),” i.e. rate or density specifications.

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

-1.66

まち

-1.55

起的

-1.51

 alterar

-1.50

‘

-1.50

to

-1.49

and

-1.47

-1.46

ty

-1.45

üb

-1.45

POSITIVE LOGITS

تیجه

1.85

芜

1.80

,'

1.73

tyfik

1.67

峦

1.65

UITextField

1.64

 見え

1.60

 appartamento

1.56

acabana

1.55

mış

1.48

Activations Density 0.004%