INDEX

Explanations

signs and 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

<0xF3>

2.32

 stabilise

1.67

 summarise

1.64

 hath

1.63

 ロング

1.58

 व्याकरण

1.55

ulla

1.52

حی

1.50

лія

1.49

 stabilisation

1.49

POSITIVE LOGITS

ँव

1.76

roud

1.73

ick

1.62

irty

1.61

্ষ

1.59

ফুল্ল

1.57

tiny

1.57

ktiv

1.55

rs

1.53

ॉर

1.52

Activations Density 0.553%