INDEX
Explanations
expressions of emotional turmoil or conflict
New Auto-Interp
Negative Logits
andro
-0.18
utar
-0.15
KF
-0.14
æĺ¨
-0.14
hmm
-0.14
inki
-0.14
isse
-0.14
azel
-0.14
issen
-0.14
utzer
-0.14
POSITIVE LOGITS
mê
0.15
consc
0.15
hist
0.14
happening
0.13
panic
0.13
jer
0.13
buck
0.13
Religious
0.13
UIT
0.13
trying
0.13
Activations Density 0.132%