INDEX
Explanations
the word "mother" or its pluralized version
New Auto-Interp
Negative Logits
ashqai
-0.76
hline
-0.72
modb
-0.69
opress
-0.68
argint
-0.67
}}">
-0.66
Karin
-0.66
].)
-0.66
Eltern
-0.66
})*/
-0.66
POSITIVE LOGITS
Holliday
0.71
Koz
0.68
Mothers
0.68
grond
0.67
transférez
0.66
Mothers
0.66
MOTHER
0.66
MOTHER
0.65
mothers
0.65
motherfucker
0.65
Activations Density 0.016%