INDEX

Explanations

PARTY MUST CITE

The neuron activates on references to legal actors or entities (e.g. “person,” “individual,” “spouse,” “entity”) in statutory or regulatory 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

DÉ

-1.38

 rapporter

-1.36

suggest

-1.34

 ſome

-1.33

 etik

-1.32

MÉ

-1.30

ようですが

-1.27

 huile

-1.24

sju

-1.23

 suggestions

-1.23

POSITIVE LOGITS

 that

1.53

of

1.48

 whose

1.45

 acompañado

1.41

who

1.37

これらの

1.31

 hingga

1.30

 След

1.30

ного

1.28

if

1.26

Activations Density 0.037%