INDEX
Explanations
negative or questioning sentiments regarding identity and perception
New Auto-Interp
Negative Logits
its
-0.27
thereof
-0.25
them
-0.24
onu
-0.23
Its
-0.23
оно
-0.21
åħ¶
-0.21
Its
-0.21
him
-0.19
bunu
-0.19
POSITIVE LOGITS
It
0.17
It
0.17
It
0.17
ñana
0.16
_it
0.16
åī²
0.15
-it
0.15
htt
0.15
fitte
0.15
FindObjectOfType
0.15
Activations Density 0.156%