INDEX

Explanations

for and to usages

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Tud

1.12

 products

1.07

 cargos

1.04

物资

0.97

 связанные

0.97

 negatives

0.96

 محصولات

0.95

 produkty

0.95

 Nintendo

0.95

 stronghold

0.95

POSITIVE LOGITS

serve

1.06

Serve

0.99

 consideración

0.95

供

0.94

 हवाले

0.90

peer

0.87

 чита

0.86

affron

0.85

ρη

0.85

Pairs

0.85

Activations Density 0.675%