INDEX

Explanations

testing code contexts

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

</u>

-1.63

 唯美

-1.62

袛

-1.57

 คุณ

-1.56

神

-1.55

趿

-1.50

 새로운

-1.47

 astounding

-1.47

 apparaît

-1.45

かっこ

-1.44

POSITIVE LOGITS

1.59

1.52

‌هایی

1.45

🤠

1.42

谩

1.38

 systems

1.37

־ה

1.35

банк

1.33

cbd

1.33

🕺

1.32

Activations Density 0.010%