INDEX

Explanations

phrases with punctuation or common suffixes

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

<unused1858>

1.58

<unused1768>

1.56

<unused1857>

1.56

<unused353>

1.53

<unused363>

1.53

<unused1877>

1.53

<unused1141>

1.52

<unused1840>

1.51

<unused111>

1.48

<unused411>

1.47

POSITIVE LOGITS

 equal

0.97

0.93

 combinations

0.83

not

0.83

0.77

0.76

iamo

0.76

rae

0.75

0.74

 ایڈ

0.73

Activations Density 0.000%