INDEX

Explanations

perhaps followed by suggestions

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

er

1.47

boi

1.44

н

1.41

ه

1.34

ver

1.27

vas

1.26

1.25

jn

1.23

hou

1.23

etah

1.23

POSITIVE LOGITS

 množ

1.78

}[(

1.76

 이는

1.74

लेषण

1.72

เฉพาะ

1.70

ಲೇ

1.70

<unused358>

1.67

 według

1.67

ंगाबाद

1.67

 pomocí

1.66

Activations Density 0.392%