INDEX

Explanations

U.S.C. or statutes

The neuron detects references to legal statutes and code sections (i.e. formal law citations with numbers and abbreviations like “Ill. Rev. Stat.” or “U.S.C. §”).

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

or

-1.20

 first

-1.16

 with

-1.10

our

-1.06

on

-1.05

when

-1.03

 because

-1.02

 their

-1.02

out

-1.00

an

-0.97

POSITIVE LOGITS

らしいです

1.40

みたいです

1.38

paravant

1.30



1.26

 lunares

1.21

几人

1.20

 actuellement

1.16

鸝

1.13

 désormais

1.13

有個

1.11

Activations Density 0.018%