INDEX
Explanations
locations and spatial prepositions
New Auto-Interp
Negative Logits
uesta
0.71
இதில்
0.70
ಾಗಿ
0.68
дами
0.68
τρέ
0.67
тами
0.65
esetén
0.65
espíritu
0.65
于
0.65
йдет
0.64
POSITIVE LOGITS
where
1.26
alongside
1.10
where
0.94
awaiting
0.91
waar
0.89
during
0.89
near
0.84
beside
0.81
hvor
0.81
beneath
0.79
Activations Density 0.431%