INDEX

Explanations

start of specific phrases

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

for

-2.22

also

-2.02

感が

-1.68

 مساء

-1.66

can

-1.66

-1.63

in

-1.60

 Publicar

-1.59

fır

-1.59

was

-1.55

POSITIVE LOGITS

_{

1.86

晅

1.86

を使用した

1.83

 использования

1.77

衎

1.76

 BERNAMA

1.75

</strong>

1.73

鈑

1.67

葑

1.66

Activations Density 0.000%