INDEX
Explanations
the presence of numerical values or identifiers
New Auto-Interp
Negative Logits
itſelf
-1.19
AsUp
-1.14
themſelves
-1.08
Mahomet
-1.03
myſelf
-1.01
ſever
-1.00
ſind
-0.98
Cæsar
-0.97
ViewImports
-0.97
+#+#
-0.93
POSITIVE LOGITS
the
0.76
"
0.74
0.72
n
0.69
N
0.66
e
0.62
“
0.62
per
0.62
F
0.60
an
0.60
Activations Density 0.082%