INDEX

Explanations

ending parts of English and Russian words

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

횃

-1.86

ޕ

-1.84

ワイト

-1.71

of

-1.67

 quantité

-1.66

 sondern

-1.63

我们是

-1.61

我没

-1.59

我没有

-1.59

ケモン

-1.59

POSITIVE LOGITS

and

2.70

to

2.41

 kuchen

1.69

’

1.65

crane

1.58

salomon

1.57

sphin

1.56

 their

1.52

subaru

1.51

 most

1.49

Activations Density 0.019%