INDEX

Explanations

short answer/poem/caption/description

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

erler

2.23

jaro

1.90

er

1.85

த்தது

1.85

ärt

1.83

asyon

1.74

ॉर्क

1.72

흰

1.72

acock

1.70

ating

1.67

POSITIVE LOGITS

resses

2.06

 ngữ

2.05

Statements

2.00

 Doct

1.97

বেলা

1.97

⌇

1.96

rage

1.92

CODE

1.92

code

1.92

物の

1.91

Activations Density 0.725%