INDEX
Explanations
mentions of a person named Gary with increasing strength in activation
occurrences of the name "Gary" in various contexts
New Auto-Interp
Negative Logits
orship
-0.77
ectar
-0.75
ored
-0.72
ilation
-0.72
ors
-0.71
ĺħ
-0.71
orial
-0.70
xual
-0.69
ylum
-0.69
semble
-0.69
POSITIVE LOGITS
Johnson
1.01
Neville
0.97
Sheffield
0.92
Cohn
0.91
Gy
0.86
Cooper
0.85
Hir
0.79
Becker
0.79
Cohen
0.78
Webb
0.77
Activations Density 0.035%