INDEX
Explanations
instances of personal pronouns and phrases indicating personal experiences or actions
New Auto-Interp
Head Attr Weights
0:0.01
1:0.02
2:0.06
3:0.18
4:0.01
5:0.03
6:0.05
7:0.17
8:0.13
9:0.10
10:0.05
11:0.13
Negative Logits
largeDownload
-1.48
haar
-1.45
actionDate
-1.36
atility
-1.23
eps
-1.23
Tier
-1.19
oreal
-1.19
edge
-1.18
atile
-1.17
イト
-1.15
POSITIVE LOGITS
slightest
1.32
contact
1.22
arrived
1.17
eve
1.17
acquaintance
1.14
encountering
1.14
diapers
1.14
arrival
1.13
onset
1.11
booking
1.10
Activations Density 0.014%