INDEX
Explanations
references to social issues and the emotional impact of events
New Auto-Interp
Negative Logits
userdata
-0.17
userID
-0.14
unity
-0.14
unes
-0.14
.Aggressive
-0.14
userid
-0.13
ÑĥÑģа
-0.13
aÄį
-0.13
eid
-0.13
hani
-0.13
POSITIVE LOGITS
U
1.38
U
0.97
u
0.94
,U
0.80
.U
0.79
_u
0.79
.u
0.77
-U
0.77
_U
0.73
/U
0.73
Activations Density 0.429%