INDEX

Explanations

export class statements

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

 многих

-1.88

-1.83

 dotyczą

-1.70

mē

-1.54

 współpracy

-1.53

 厂家

-1.51

 všem

-1.51

だったので

-1.50

-1.49

 我们

-1.48

POSITIVE LOGITS

 However

1.69

of

1.53

 There

1.44

',

1.44

there

1.40

 betra

1.38

 that

1.38

ita

1.37

la

1.37

li

1.36

Activations Density 0.002%