INDEX

Explanations

numbers following "No."

The neuron detects numbered reference markers—tokens like “No.”/“Nos.” and adjoining digits that indicate document, grant, patent, or case identification numbers.

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

These

-2.09

Those

-2.00

One

-1.85

 presumably

-1.83

 utterly

-1.83

Just

-1.82

and

-1.81

 primarily

-1.79

Two

-1.78

Different

-1.73

POSITIVE LOGITS

翆

1.88

玙

1.84

⎔

1.77

狴

1.73

虓

1.71



1.69

翃

1.67

遊んで

1.66

 améli

1.66

 USING

1.66

Activations Density 0.074%