INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rainbows

0.79

စိတ်

0.76

 피해

0.73

pheromone

0.72

 hemolysis

0.72

 heuristic

0.71

 montage

0.71

楹

0.71

 matahari

0.70

তাবাদ

0.70

POSITIVE LOGITS

 thick

2.24

thick

1.80

 firm

1.74

 dense

1.73

 soft

1.70

 thicker

1.68

 Thick

1.62

 stiff

1.61

 thin

1.57

 plump

1.55

Activations Density 1.702%

No Known Activations