INDEX

Explanations

Russian words and phrases

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

 there

-1.84

 они

-1.62

 mereka

-1.58

not

-1.55

});

-1.52

 They

-1.49

--;

-1.48

to

-1.45

it

-1.38

 Иванович

-1.38

POSITIVE LOGITS

 haupts

1.77

 queridos

1.76



1.73

 fantasmas

1.72

 resultant

1.53

幾乎

1.53

 regard

1.52

März

1.51

すご

1.50

をする

1.49

Activations Density 0.009%