INDEX
Explanations
names of people and their relationships
New Auto-Interp
Negative Logits
Jeremy
-0.60
Timmy
-0.59
Damien
-0.57
Josh
-0.56
Timmy
-0.56
Jeremy
-0.55
Mikey
-0.54
eloma
-0.54
Josh
-0.54
lads
-0.54
POSITIVE LOGITS
Ann
0.91
Ann
0.77
LOTTE
0.73
Anne
0.71
actress
0.71
ANN
0.69
Margaret
0.69
María
0.67
Elizabeth
0.67
netje
0.67
Activations Density 0.942%