INDEX
Explanations
names related to the actor Marlon Brando
references to significant events or actions related to individuals
New Auto-Interp
Negative Logits
GN
-0.89
CU
-0.84
tot
-0.81
IC
-0.79
chens
-0.75
CU
-0.75
icter
-0.73
GN
-0.73
CHO
-0.70
OTE
-0.69
POSITIVE LOGITS
Mar
2.51
Mar
2.29
mar
1.98
mar
1.94
MAR
1.92
MAR
1.88
Marin
1.51
Marino
1.41
Apr
1.39
Apr
1.31
Activations Density 0.165%