INDEX
Explanations
mentions of the name "Davis"
mentions of the name "Davis."
New Auto-Interp
Negative Logits
ãĥĥãĥĪ
-0.81
Tayyip
-0.73
ugal
-0.69
ilater
-0.67
horizon
-0.66
bably
-0.66
cies
-0.65
lopp
-0.65
liest
-0.65
liness
-0.64
POSITIVE LOGITS
Davis
1.20
Davis
1.05
Hanson
0.85
acre
0.84
ville
0.83
essa
0.82
mouth
0.79
den
0.75
pole
0.74
Webb
0.74
Activations Density 0.008%