INDEX
Explanations
expressing possibility or uncertainty
New Auto-Interp
Negative Logits
basically
0.49
praticamente
0.47
होईल
0.46
stets
0.46
prácticamente
0.44
基本上
0.43
essentially
0.42
据说
0.42
往往
0.42
ก็จะ
0.42
POSITIVE LOGITS
algún
0.99
algum
0.95
可能是
0.91
perhaps
0.90
alguma
0.90
possibly
0.89
možda
0.89
somehow
0.88
perhaps
0.87
possibly
0.86
Activations Density 0.063%