INDEX

Explanations

examine oneself or others

self possession and individuality

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 змо

0.39

 ਇਹ

0.38

 जितने

0.37

 সম্ভবত

0.37

 сами

0.36

 कमाल

0.36

आम

0.35

ഈ

0.35

 aast

0.35

 ഡോ

0.34

POSITIVE LOGITS

 oneself

2.59

 ones

1.33

 Ones

1.25

ones

1.22

your

1.19

 your

1.18

你的

1.13

 kita

1.02

あなたの

1.02

 당신

0.98

Activations Density 0.417%