INDEX
Explanations
mentions of the word "regular"
references to the term "regular" in various contexts
New Auto-Interp
Negative Logits
Sov
-0.74
lda
-0.70
ï¸ı
-0.66
IRO
-0.65
obal
-0.63
arta
-0.63
agos
-0.62
UST
-0.61
ye
-0.60
Mb
-0.60
POSITIVE LOGITS
ity
1.16
ised
1.00
ization
0.98
cy
0.97
isation
0.95
izing
0.92
ITY
0.90
weekday
0.87
ities
0.86
ized
0.86
Activations Density 0.022%