INDEX
Explanations
emotional reactions and sentiments expressed in the text
New Auto-Interp
Negative Logits
u
-0.16
wear
-0.16
ordes
-0.15
kup
-0.15
em
-0.15
NR
-0.14
ika
-0.14
iry
-0.14
od
-0.14
ems
-0.13
POSITIVE LOGITS
ness
0.20
NESS
0.17
reste
0.15
nicos
0.14
_lineno
0.14
/lic
0.14
ahir
0.14
HeaderCode
0.14
essian
0.14
ooter
0.14
Activations Density 0.200%