INDEX

Explanations

keywords and 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

妩

-1.14

チール

-1.02

 recevrez

-1.02

siguiente

-1.01

 surpresa

-1.00

 actuellement

-0.98

august

-0.96

 discussione

-0.95

ῖς

-0.95

 construção

-0.94

POSITIVE LOGITS

 that

1.29

 before

1.21

setBold

1.08

цена

0.99

 که

0.99

 Titans

0.96

Salz

0.95

 Before

0.94

hoe

0.94

랍

0.92

Activations Density 0.008%