INDEX
Explanations
phrases related to login actions and user engagement in digital platforms
New Auto-Interp
Head Attr Weights
0:0.05
1:0.03
2:0.12
3:0.07
4:0.18
5:0.03
6:0.02
7:0.02
8:0.19
9:0.16
10:0.05
11:0.02
Negative Logits
SPONSORED
-1.53
alter
-1.41
alon
-1.27
bom
-1.22
focal
-1.20
stru
-1.20
torn
-1.17
disadvant
-1.13
cially
-1.12
neutral
-1.12
POSITIVE LOGITS
rocal
1.48
captcha
1.39
76561
1.34
Subscribe
1.26
Pastebin
1.25
Errors
1.22
ername
1.22
Void
1.21
Username
1.20
aturday
1.20
Activations Density 0.005%