INDEX

Explanations

words ending in ing

dehumanizing, degrading, threatening

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

 निकालना

0.51

ಲಾಗುತ್ತದೆ

0.50

 llevado

0.45

 செய்யப்பட்டது

0.45

ψει

0.45

isation

0.44

 việc

0.44

 рассказать

0.44

 হয়েছিল

0.43

 vermek

0.43

POSITIVE LOGITS

izing

1.75

ifying

1.51

ising

1.50

ating

1.46

ulating

1.45

IZING

1.45

ISING

1.34

ující

1.30

uating

1.30

ATING

1.27

Activations Density 0.088%