INDEX
Explanations
the name "Lov" appearing in various contexts
mentions of the concept of "love."
New Auto-Interp
Negative Logits
PART
-0.70
deviations
-0.64
Tempest
-0.64
IZE
-0.63
restraints
-0.63
Barbar
-0.62
deviation
-0.59
corpor
-0.58
Phant
-0.58
fever
-0.58
POSITIVE LOGITS
lov
1.21
ingly
1.19
estones
1.01
estone
0.98
icz
0.97
igree
0.96
ski
0.95
est
0.93
estation
0.92
gren
0.92
Activations Density 0.011%