INDEX

Explanations

spending time or money

This neuron activates on numeric tokens (integers or decimals) in the text.

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

of

-1.55

 from

-1.45

for

-1.43

มากๆ

-1.42

has

-1.40

 other

-1.38

can

-1.34

 only

-1.34

 árbitro

-1.32

 began

-1.29

POSITIVE LOGITS

</strong>

1.95

ників

1.54

</h3>

1.52

 $("#

1.37

蓠

1.35

袛

1.33

ｒ

1.30

𝔗

1.23

 Canad

1.22

 commerces

1.22

Activations Density 0.031%