INDEX

Explanations

court filing information

The neuron primarily activates on numeric tokens—dates, times, years, docket numbers, and other digit sequences.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

();

-2.20

</u>

-2.11

</th>

-1.98

":

-1.87

";

-1.86

')

-1.86

},

-1.73

();

-1.72

$.

-1.70

</strong>

-1.69

POSITIVE LOGITS

 nuits

1.44

namientos

1.41

៚

1.38

妯

1.37

迎来

1.36

 nodeId

1.34

加拿

1.34

Dimensi

1.33

 télévis

1.33

 μέχρι

1.30

Activations Density 0.028%