INDEX

Explanations

population and numbers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 daba

-0.95

 luce

-0.94

 años

-0.89

 cruz

-0.85

 rusak

-0.84

 italiano

-0.84

ଝ

-0.83

 would

-0.82

 кроме

-0.82

ССР

-0.81

POSITIVE LOGITS

適量

0.96

 acolo

0.96

and

0.91

 aici

0.89

 センター

0.88

vity

0.87

 Decrease

0.87

tabria

0.86

 gradation

0.85

verständ

0.84

Activations Density 0.008%