INDEX
Explanations
prepositions followed by locations
New Auto-Interp
Negative Logits
高雄
0.49
Beograd
0.45
Osaka
0.44
СПб
0.43
maroc
0.43
केजरीवाल
0.42
Lond
0.42
गुजरात
0.42
Gujarat
0.41
Putin
0.41
POSITIVE LOGITS
neighboring
0.37
eastern
0.34
mainstream
0.34
mainland
0.34
North
0.34
nearby
0.34
Latin
0.33
predominantly
0.32
Japan
0.31
ially
0.31
Activations Density 0.307%