INDEX

Explanations

Linux operating system

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

 muñ

2.43

 spust

2.37

ِي

2.24

 مشرقی

2.22

КУ

2.21

टीसी

2.16

ར

2.13

чику

2.12

ِی

2.10

ｺ

2.09

POSITIVE LOGITS

2.62

য়ের

1.94

sal

1.88

ති

1.77

sü

1.76

ன்மை

1.72

lished

1.70

мель

1.69

য়ের

1.65

स्था

1.63

Activations Density 0.003%