INDEX

Explanations

work or construction beginning

The neuron activates on numeric expressions (digits, years, measurements) 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

 wants

-1.35

if

-1.35

 uses

-1.34

那些

-1.32

</h3>

-1.30

$,

-1.29

 those

-1.28

'],$

-1.28

 both

-1.27

annia

-1.26

POSITIVE LOGITS

 rimane

1.41

意外と

1.36

你这

1.35

 ebbe

1.34

ーズン

1.32

 amazingly

1.31

okohama

1.30

蛱

1.30

一个小

1.30

ataires

1.28

Activations Density 0.053%