INDEX

Explanations

physical origin, properties, and nature

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

久しぶり

-1.66

小伙伴

-1.64

 destrucción

-1.52

 supervivencia

-1.50

ländische

-1.49

ский

-1.48

 PARTICULAR

-1.47

ᥬ

-1.46

 отделение

-1.45

ッティング

-1.44

POSITIVE LOGITS

in

1.72

 mosso

1.67

 nuov

1.60

 pulsante

1.56

1.55

 sentito

1.55

))$_

1.52

鏵

1.50

 these

1.50

Activations Density 0.020%