INDEX
Explanations
phrases related to time
references to experiences and activities over time
New Auto-Interp
Head Attr Weights
0:0.06
1:0.03
2:0.18
3:0.07
4:0.05
5:0.08
6:0.06
7:0.03
8:0.22
9:0.10
10:0.05
11:0.02
Negative Logits
unification
-1.41
elig
-1.35
gain
-1.33
ajo
-1.19
precedence
-1.12
catentry
-1.12
descendants
-1.12
Jose
-1.09
Appeal
-1.09
idency
-1.09
POSITIVE LOGITS
��
1.59
ゼ
1.29
uzz
1.23
ha
1.21
ーク
1.18
lished
1.18
laughing
1.17
REAM
1.17
/+
1.14
warn
1.14
Activations Density 0.063%