INDEX

Explanations

hard

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.80

 unknownFields

-0.75

 avoient

-0.73

 africains

-0.68

IntoConstraints

-0.67

 étoient

-0.67

 étoit

-0.65

__*/

-0.65

}>;

-0.64

 Também

-0.63

POSITIVE LOGITS

so

1.02

so

0.67

 так

0.57

matory

0.57

så

0.54

новништво

0.51

SO

0.49

So

0.48

MLLoader

0.47

はじめに

0.47

Activations Density 0.005%