INDEX

Explanations

accuracy

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Accuracy

-0.72

 Accuracy

-0.69

neté

-0.65

 jScrollPane

-0.59

 accuracy

-0.55

/**

-0.52

accuracy

-0.52

})}

-0.48

 Likelihood

-0.46

Launching

-0.46

POSITIVE LOGITS

Tikang

0.75

 class

0.72

 Class

0.63

class

0.60

Class

0.57

 kelas

0.56

CLASS

0.54

 classes

0.54

 klasse

0.54

 CLASS

0.53

Activations Density 0.038%