INDEX

Explanations

all [noun]

The neuron activates on numeric tokens (integers or decimals), detecting numbers and statistical figures.

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

 also

-1.95

↵

-1.58

 コンパクト

-1.53

ſu

-1.38

 perfecte

-1.35

 obtenidos

-1.27

 suppos

-1.27

橚

-1.23

 protože

-1.22

鞋

-1.21

POSITIVE LOGITS

 which

1.59

for

1.59

 from

1.52

 terkenal

1.46

of

1.42

in

1.41

 berpikir

1.41

 prêtres

1.40

 menyukai

1.39

as

1.36

Activations Density 0.039%