INDEX
Explanations
beginning of sentence or clause
New Auto-Interp
Negative Logits
SequentialGroup
-0.77
beziehen
-0.76
不出
-0.75
aortic
-0.74
fistula
-0.74
utivo
-0.73
flexibility
-0.73
ximate
-0.72
())),
-0.72
댑
-0.71
POSITIVE LOGITS
intercepts
0.88
intercept
0.88
Thru
0.84
salam
0.74
मिल
0.74
zach
0.73
dedicar
0.73
0.72
fz
0.69
detenido
0.69
Activations Density 0.007%