INDEX

Explanations

web development imports

The neuron fires on hyphens in package or module names (e.g. in import/require paths with “-”).

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

倘

-1.99

by

-1.94

if

-1.82

or

-1.71

is

-1.70

 either

-1.67

in

-1.64

-1.59

can

-1.55

 could

-1.55

POSITIVE LOGITS

 hombro

1.63

Charsets

1.59

豳

1.59

福井

1.57

ACTERS

1.55

eux

1.55

栃

1.48

を設定

1.47

 撮っ

1.46

 maisons

1.45

Activations Density 0.003%