INDEX
Explanations
references to spiritual or religious themes and concepts
New Auto-Interp
Negative Logits
unami
-0.16
ucu
-0.15
rikes
-0.15
rike
-0.15
833
-0.15
connexion
-0.14
žel
-0.14
uerdo
-0.14
358
-0.14
Elsa
-0.14
POSITIVE LOGITS
venta
0.19
Adjust
0.18
Personality
0.16
Isle
0.16
buffers
0.15
ellig
0.15
Ur
0.15
personality
0.14
planet
0.14
Father
0.14
Activations Density 0.003%