INDEX

Explanations

names and abbreviations

The neuron fires on occurrences of the substring “swing,” as in references to the Java Swing library.

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

If

-2.17

-1.87

You

-1.76

-1.74

 Each

-1.73

Each

-1.70

 Both

-1.69

-1.65

↵↵↵

-1.61

{*}

-1.59

POSITIVE LOGITS

</h2>

2.30

闥

1.77

 Schriftsteller

1.72

asının

1.70

 negativa

1.65

愆

1.61

collants

1.55

ecé

1.54

 Politiker

1.50

ujem

1.48

Activations Density 0.000%