INDEX

Explanations

assertions and static_assert

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

us

-1.98

-1.85

-1.76

Our

-1.69

he

-1.68

for

-1.60

↵

-1.59

ate

-1.56

For

-1.55

ga

-1.52

POSITIVE LOGITS

こんな感じで

1.66

髕

1.65

ichtete

1.63

 burbu

1.62

 EXPEND

1.61

ghế

1.61

anément

1.60

 dapat

1.60

ༀ

1.60

各样的

1.59

Activations Density 0.003%