INDEX

Explanations

normalization and permissiveness

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

 Instrum

1.81

 offert

1.78

σιμοποι

1.75

 objRequest

1.69

勰

1.67

>';

1.66

 поряд

1.65

 suerte

1.64

Repost

1.63

 terang

1.63

POSITIVE LOGITS

est

1.74

ઓ

1.69

рма

1.63

čk

1.50

\"]

1.49

 toler

1.48

гава

1.47

ცხ

1.46

ung

1.46

atives

1.45

Activations Density 0.507%