INDEX
Explanations
instances of emotional responses or sentiments expressed in the context of disappointment or discontent
New Auto-Interp
Negative Logits
P
-0.57
Its
-0.56
I
-0.56
↵↵
-0.56
We
-0.54
*
-0.52
#
-0.50
UnknownFields
-0.50
%
-0.49
WebServlet
-0.49
POSITIVE LOGITS
“
0.88
itſelf
0.87
ſelves
0.77
houſe
0.76
myſelf
0.76
himſelf
0.76
uſe
0.74
juſt
0.74
ſtill
0.73
beſt
0.72
Activations Density 0.160%