INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

273,612 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

粳

0.75

 dumplings

0.72

 pivoted

0.71

 kidnapped

0.70

 incarcerated

0.69

 ores

0.68

 Giri

0.66

ಘ

0.66

铡

0.65

稈

0.64

POSITIVE LOGITS

 Paint

1.75

 paint

1.75

 coating

1.70

 Coating

1.67

 Coatings

1.65

 coatings

1.60

paint

1.60

Paint

1.58

 paints

1.52

 Painting

1.47

Activations Density 0.821%

No Known Activations