INDEX
Explanations
mentions of a specific individual or entity named "Davis"
references to an individual named Davis
New Auto-Interp
Negative Logits
ãĥĥãĥĪ
-0.76
ikarp
-0.69
liest
-0.69
emort
-0.68
Seym
-0.68
lopp
-0.68
bably
-0.67
liness
-0.67
ugal
-0.66
cies
-0.66
POSITIVE LOGITS
Davis
1.05
Hanson
0.91
Davis
0.90
essa
0.85
Webb
0.83
ville
0.78
eland
0.75
den
0.74
acre
0.73
ragon
0.73
Activations Density 0.015%