INDEX
Explanations
references to the Filipino culture and community
New Auto-Interp
Negative Logits
engin
-0.17
itori
-0.17
oris
-0.17
icle
-0.16
ality
-0.15
Tier
-0.15
ham
-0.15
392
-0.15
itor
-0.14
tier
-0.14
POSITIVE LOGITS
inos
0.21
ippines
0.21
ippi
0.20
agma
0.19
inx
0.18
ipp
0.18
inas
0.18
-American
0.17
å¾ĭ宾
0.16
Fil
0.16
Activations Density 0.005%