INDEX

Explanations

list of items

The neuron fires on code fragments that define literal collections of numeric values (e.g. array or list initializers containing numbers).

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

We

-1.75

-1.74

 While

-1.70

In

-1.69

-1.55

-1.52

-1.48

or

-1.43

 Since

-1.41

FOR

-1.41

POSITIVE LOGITS

訁

1.95

 GARANT

1.72

ಱ

1.63

 ABBRE

1.62

瘊

1.59

 independente

1.52

𐀀

1.51

}))

1.45

 significativos

1.43

 befre

1.41

Activations Density 0.022%