INDEX
Explanations
references to Martin Luther King Jr. and related mentions of his legacy
New Auto-Interp
Negative Logits
usta
-0.19
neys
-0.16
ike
-0.15
ies
-0.15
abras
-0.15
oble
-0.14
Riv
-0.14
adan
-0.14
French
-0.14
@"\
-0.14
POSITIVE LOGITS
King
0.27
King
0.23
ãĤŃãĥ³ãĤ°
0.22
KING
0.22
king
0.21
king
0.19
Kings
0.18
Jr
0.17
Luther
0.16
ancock
0.15
Activations Density 0.004%