INDEX

Explanations

No Explanations Found

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

 لوبو

1.55

Artifact

1.53

TaskPojo

1.52

剤

1.50

 ہمس

1.46

菪

1.45

ـ

1.43

 سایټ

1.43

SanPham

1.41

轎

1.39

POSITIVE LOGITS

 rotation

1.17

 image

1.06

 bond

1.04

 asymmetric

1.00

 curvature

0.98

 base

0.97

 asymmetrical

0.97

 conversion

0.96

 selection

0.96

 alignment

0.95

Activations Density 0.003%

No Known Activations