INDEX
Explanations
references to famous artists and their works
Leonardo Vinci Mona
New Auto-Interp
Negative Logits
Barbour
-0.43
τρο
-0.41
inander
-0.40
buty
-0.39
الحره
-0.38
épreuve
-0.38
teira
-0.38
hendak
-0.37
referrerpolicy
-0.37
permum
-0.36
POSITIVE LOGITS
Vinci
1.72
Vinci
1.45
vinci
1.14
Leonardo
0.99
Leonardo
0.89
Mona
0.85
leonardo
0.79
Michelangelo
0.71
Mona
0.71
mona
0.69
Activations Density 0.005%