INDEX
Explanations
imperative verbs indicating action
New Auto-Interp
Head Attr Weights
0:0.09
1:0.08
2:0.07
3:0.07
4:0.09
5:0.07
6:0.07
7:0.07
8:0.09
9:0.08
10:0.08
11:0.08
Negative Logits
morph
-2.39
motif
-2.06
�
-1.95
rint
-1.91
incorporation
-1.91
toler
-1.88
characteristic
-1.87
yles
-1.86
characteristics
-1.85
physi
-1.84
POSITIVE LOGITS
Cheong
2.31
enium
2.26
anke
2.24
Cairo
2.07
orgetown
2.06
outheast
2.03
Corona
1.98
obin
1.97
�
1.95
Nile
1.95
Activations Density 0.000%