INDEX

Explanations

code structure context

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

 ۱۷

-1.45

“)

-1.44

 装修

-1.43

 борьбе

-1.42

ements

-1.41

 five

-1.35

 chanteur

-1.35

 було

-1.32

さは

-1.32

倂

-1.30

POSITIVE LOGITS

 больших

1.83

 Tanto

1.61

 baseado

1.56

 conséquent

1.55

なかな

1.52

1.50

 replies

1.45

 pomysł

1.42

 всегда

1.41

 последних

1.41

Activations Density 0.010%