INDEX
Explanations
references to full-time and part-time employment
New Auto-Interp
Negative Logits
ube
-0.15
argent
-0.15
enas
-0.15
bane
-0.15
اسÙħ
-0.14
alam
-0.14
sein
-0.14
ÐĿаз
-0.14
ابÛĮ
-0.13
ç«ĭãģ¡
-0.13
POSITIVE LOGITS
/full
0.20
452
0.17
plit
0.15
ÑĥÑģа
0.15
ìŁģ
0.14
vyk
0.14
/part
0.14
ìĶ©
0.14
devoted
0.14
ãĥ«ãĥĪ
0.13
Activations Density 0.010%