INDEX

Explanations

float literals followed by punctuation

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



-2.08

巿

-2.00

 these

-1.98

 categorized

-1.95

ၟ

-1.95

 ragaz

-1.80

晅

-1.77

 definitively

-1.73

⃨

-1.73

 eccellente

-1.72

POSITIVE LOGITS

 первое

1.67

();*/

1.66

一個

1.63

 остальные

1.63

 proporcion

1.60

 {}));

1.59

ので

1.59

 неделю

1.58

1.55

 пять

1.55

Activations Density 0.001%