INDEX

Explanations

UI widget names in code

The neuron detects references to Android UI component class names (e.g. widgets and view types) in import statements.

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

izace

-1.67

-1.59

 Öffnen

-1.59

all

-1.57

-1.52

 until

-1.46

so

-1.44

已是

-1.41

-1.39

 recientes

-1.38

POSITIVE LOGITS

 orec

1.57

㉗

1.53

あなたの

1.49

他

1.48

కర్య

1.43

 sarı

1.41

 Juventud

1.40

 Trouver

1.40

 Embaj

1.39

Haben

1.38

Activations Density 0.006%