INDEX

Explanations

further investigation, reading, learning, information

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

ेडियम

2.89

াহিয়া

2.83

লাইয়া

2.62

okatokat

2.46

 imaju

2.41

ઉસ

2.40

嚜

2.38

पूर्ति

2.37

ęcia

2.37

ද්ග

2.36

POSITIVE LOGITS

ev

1.80

tir

1.80

“

1.78

ej

1.74

„

1.70

vine

1.68

 mixed

1.62

ide

1.55

Lik

1.53

gu

1.51

Activations Density 0.050%