INDEX

Explanations

issues and problems

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

 trainings

-1.92

 pastas

-1.82

 equipments

-1.73

 breads

-1.67

 advices

-1.65

 evidences

-1.43

 loosing

-1.42

 Ebay

-1.41

 whatsapp

-1.34

 both

-1.30

POSITIVE LOGITS

Suppose

1.57

‌

1.55

 به‌

1.35

 Suppose

1.27

1.23

 Türkiye

1.23

 Afterward

1.20

androidx

1.18

さまざまな

1.17

 afterward

1.15

Activations Density 0.031%