instances of the word "to" indicating actions or submissions

New Auto-Interp

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ワン

-0.96

覚醒

-0.86

 freely

-0.77

グ

-0.75

 cheaply

-0.74

leeve

-0.71

bodied

-0.69

accessible

-0.68

 furiously

-0.67

POSITIVE LOGITS

 Michele

0.75

 Polit

0.73

us

0.71

me

0.71

 POLITICO

0.70

 Manny

0.70

 Danielle

0.69

 Ralph

0.68

 Northwestern

0.68

 Herb

0.68

Activations Density 0.211%