INDEX
Explanations
negative experiences or sentiments related to products or services
New Auto-Interp
Negative Logits
or
-0.17
uf
-0.16
ir
-0.16
of
-0.15
&
-0.14
amed
-0.14
ied
-0.14
ared
-0.14
ia
-0.14
ire
-0.14
POSITIVE LOGITS
It
0.23
This
0.22
The
0.22
In
0.22
They
0.22
This
0.22
They
0.21
It
0.21
There
0.21
These
0.21
Activations Density 0.090%