INDEX
Explanations
estimates and approximate quantities
New Auto-Interp
Negative Logits
அப்படி
0.35
beitung
0.32
детям
0.31
赅
0.31
ೇನೆ
0.31
jelasan
0.31
_.
0.31
ነት
0.30
ajati
0.30
说明
0.30
POSITIVE LOGITS
nine
0.52
approximately
0.51
около
0.50
approximately
0.47
eight
0.47
حوالي
0.46
seven
0.46
ประมาณ
0.45
około
0.45
約
0.44
Activations Density 0.095%