INDEX

Explanations

legal citations and identifiers

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

and

-2.67

-1.77

of

-1.76

･･

-1.66

to

-1.55

categorized

-1.55

In

-1.54

ubahan

-1.51

以後

-1.50

If

-1.49

POSITIVE LOGITS

鎏

1.91

了许多

1.91

imetry

1.85

鸶

1.84

ième

1.83

γραφή

1.83

嗌

1.81

rées

1.80

ůli

1.80

kennen

1.79

Activations Density 0.000%