INDEX
Explanations
references to poverty and struggles associated with it
New Auto-Interp
Negative Logits
ianum
-0.41
endi
-0.39
va
-0.39
Lloyd
-0.38
Acc
-0.37
contr
-0.36
GL
-0.36
Dziękuję
-0.36
riti
-0.35
disemb
-0.35
POSITIVE LOGITS
pobreza
0.65
poverty
0.61
hambre
0.61
Inscrivez
0.58
noDo
0.57
hunger
0.57
poverty
0.57
hunger
0.56
Poverty
0.52
Poverty
0.52
Activations Density 0.405%