INDEX

Explanations

verbs followed by articles or prepositions

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

 they

-2.14

of

-1.89

-1.84

 можно

-1.70

when

-1.65

 можна

-1.64

we

-1.63

 iedereen

-1.55

 when

-1.55

нятие

-1.51

POSITIVE LOGITS

1.80

?,

1.66

“

1.62

matisch

1.59

であり

1.55

'=>'

1.54

'}

1.53

'>{

1.53

”?

1.49

』『

1.49

Activations Density 0.002%