INDEX
Negative Logits
களை
0.41
相手
0.40
qdm
0.39
partners
0.39
icmp
0.39
well
0.38
Preferred
0.38
objects
0.38
partner
0.38
preferred
0.37
POSITIVE LOGITS
others
0.86
Others
0.70
Others
0.68
其他人
0.67
others
0.64
advising
0.59
someone
0.56
दूसरों
0.55
他人
0.54
alguém
0.54
Activations Density 0.084%