INDEX
Explanations
specific details or incidents that the speaker remembers
phrases expressing recall or memory related to past events
New Auto-Interp
Head Attr Weights
0:0.08
1:0.04
2:0.07
3:0.09
4:0.05
5:0.09
6:0.05
7:0.03
8:0.24
9:0.09
10:0.08
11:0.03
Negative Logits
vc
-1.23
izons
-1.20
origin
-1.19
req
-1.16
thumbnails
-1.16
nm
-1.14
xi
-1.12
estyles
-1.08
xp
-1.07
owered
-1.07
POSITIVE LOGITS
terday
1.39
Tanz
1.13
proverb
1.11
LAST
1.07
nostalg
1.07
memor
1.07
rhy
1.05
Azerb
1.04
autobiography
1.04
firsthand
1.04
Activations Density 0.048%