INDEX

Explanations

legal citations and numbers

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

 pericolo

-0.73

ведений

-0.72

 avrebbe

-0.70

sibilità

-0.70

🌒

-0.69

 fals

-0.69

حداث

-0.69

Hod

-0.68

 rapporto

-0.68

 riconoscimento

-0.67

POSITIVE LOGITS

CF

1.19

CF

1.17

AF

1.17

BF

1.15

TF

1.06

PF

1.05

PF

1.01

BF

0.98

SF

0.97

SF

0.97

Activations Density 0.101%