INDEX
Explanations
punctuation marks, particularly commas
New Auto-Interp
Head Attr Weights
0:0.08
1:0.07
2:0.08
3:0.07
4:0.08
5:0.09
6:0.08
7:0.08
8:0.09
9:0.08
10:0.09
11:0.07
Negative Logits
Motion
-2.41
plurality
-2.20
eal
-2.15
emoji
-2.06
-1.97
′
-1.97
igned
-1.97
deficit
-1.96
-1.95
shortfall
-1.94
POSITIVE LOGITS
atown
2.25
iku
2.23
�
2.19
ritz
2.19
eport
2.17
iland
2.15
thood
2.12
Psy
2.10
izons
2.09
龍喚士
2.08
Activations Density 0.000%