INDEX

Explanations

explaining or exemplifying

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

la

-1.88

 accomplice

-1.85

 mereka

-1.83

坶

-1.75

ߠ

-1.74

кономі

-1.72

杁

-1.70

 参考

-1.67

 المختلفة

-1.66

绒

-1.66

POSITIVE LOGITS

 they

2.47

2.36

2.08

we

1.73

\"

1.69

\'

1.63

eynman

1.60

¹

1.59

."

1.59

rijven

1.59

Activations Density 0.031%