INDEX

Explanations

various content types

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

 Тому

0.83

 Deshalb

0.81

反而

0.78

льник

0.77

 свое

0.77

лда

0.76

 nedenle

0.75

#__

0.74

 bedeutet

0.74

 Enquanto

0.74

POSITIVE LOGITS

 various

1.95

various

1.88

 varying

1.84

 ranging

1.82

各种

1.76

 berbagai

1.75

 různých

1.70

各種

1.68

 Various

1.60

 다양한

1.60

Activations Density 0.314%