INDEX

Explanations

quantities followed by nouns

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

 Leute

-1.02

場所で

-1.00

 yerde

-0.95

for

-0.94

 tasas

-0.91

也不

-0.90

 großer

-0.89

and

-0.89

-0.87

-0.86

POSITIVE LOGITS

Better

1.12

לית

1.10

augmenter

1.03

knecht

0.97

gün

0.96

🐰

0.94

cension

0.94

 Komun

0.92

 Río

0.92

 της

0.91

Activations Density 0.042%