INDEX

Explanations

well- designed, documented, supported

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 وح

1.96

ا

1.89

ن

1.80

 Increased

1.79

 και

1.78

ϛ

1.76

خ

1.76

 শ্রবণ

1.76

 इत्यादि

1.75

 δεν

1.74

POSITIVE LOGITS

 জানায়

1.59

↵↵↵↵↵↵

1.56

↵↵↵

1.56

↵↵↵↵↵

1.51

ለያ

1.48

↵↵↵↵

1.46

 spoloč

1.45

↵↵↵↵↵↵↵

1.38

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.37

ďaka

1.37

Activations Density 0.102%