INDEX

Explanations

court case citations

The neuron responds to lines that look like formal legal case headings or citations—e.g. court names, docket numbers, parties, and other metadata presented in all-caps formatting.

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

 their

-1.52

</strong>

-1.37

 other

-1.35

 الأخرى

-1.34

 Terima

-1.33

 Semoga

-1.32

 Mungkin

-1.31

dáms

-1.30

Sebelumnya

-1.30

嫱

-1.27

POSITIVE LOGITS

 about

1.54

1.42

CI

1.31

⩕

1.30

that

1.30

EN

1.24

 gebruik

1.23

AS

1.23

 необходимые

1.23

AND

1.22

Activations Density 0.111%