INDEX
Explanations
beach images, trip, vacation
New Auto-Interp
Negative Logits
The
0.94
Ка
0.93
ﺮ
0.91
ων
0.85
ﻮ
0.84
the
0.82
Ба
0.82
ре
0.81
ﺩ
0.81
T
0.79
POSITIVE LOGITS
h
1.11
Beach
1.05
is
0.98
I
0.97
(
0.93
y
0.93
0.93
</h3>
0.90
$
0.87
um
0.84
Activations Density 0.004%