INDEX

Explanations

legal license agreements

The neuron activates on licensing boilerplate, especially Apache License headers and related terms.

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

 упаковка

-1.92

 Thanks

-1.89

 perché

-1.88

 What

-1.84

 When

-1.83

énus

-1.83

-1.82

ны

-1.80

-1.78

 wenn

-1.71

POSITIVE LOGITS

兩

2.06

1.88

 фильме

1.81

让他们

1.77

 diki

1.74

所说

1.73

 idiota

1.71

Olvid

1.70

取决

1.70

ﹶ

1.67

Activations Density 0.216%