INDEX
Explanations
references to governmental or community services and initiatives
New Auto-Interp
Negative Logits
ullah
-0.16
BORDER
-0.15
uo
-0.15
.builders
-0.15
Tunis
-0.14
phem
-0.14
jane
-0.14
peter
-0.14
Tory
-0.14
Tehran
-0.14
POSITIVE LOGITS
Filipino
0.44
Filip
0.44
Fil
0.43
Fil
0.40
Philippines
0.37
Philippine
0.37
fil
0.36
Manila
0.36
FIL
0.35
Phil
0.34
Activations Density 0.046%