INDEX
Explanations
mentions or references to the word "Mother"
mentions of "Mother," likely associated with maternal themes or figures
New Auto-Interp
Negative Logits
EY
-1.03
NRS
-0.90
ickr
-0.83
RAFT
-0.81
=-=-=-=-=-=-=-=-
-0.78
ORN
-0.76
OPLE
-0.75
EFF
-0.73
yz
-0.73
SELECT
-0.72
POSITIVE LOGITS
Mother
1.20
mother
1.08
Mother
1.04
ship
0.86
Joy
0.85
Mama
0.83
Daughter
0.83
Eater
0.81
Mothers
0.78
unia
0.78
Activations Density 0.008%