INDEX

Explanations

class declaration or method call

The neuron detects numeric tokens—e.g. list-item numbers, version numbers, or other standalone digits.

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

 tendremos

-1.38

。

-1.30

 не

-1.28

 THERE

-1.28

pplung

-1.27

かれています

-1.26

 told

-1.21

—

-1.20

fficio

-1.18

同比

-1.16

POSITIVE LOGITS

楫

1.44

 cansado

1.40

 paiement

1.37

izator

1.36

豆

1.28

meisters

1.25

 寿司

1.23

 hvad

1.23

 parcs

1.23

tened

1.22

Activations Density 0.245%