INDEX
Explanations
phrases related to complaints or grievances
New Auto-Interp
Negative Logits
VIC
-0.20
ales
-0.19
aho
-0.17
vic
-0.15
ic
-0.15
upt
-0.15
oping
-0.15
knots
-0.14
ocks
-0.14
æĪ
-0.14
POSITIVE LOGITS
zcze
0.14
ICTURE
0.14
ertia
0.14
oppins
0.14
.cgi
0.14
unity
0.14
currentColor
0.13
iskey
0.13
Warn
0.13
ylon
0.13
Activations Density 0.036%