INDEX
Explanations
mentions of the word "mam" and its variations, indicating a focus on maternal or familial references
New Auto-Interp
Negative Logits
issen
-0.15
iner
-0.15
iddy
-0.15
witter
-0.14
/share
-0.14
Tactics
-0.14
coni
-0.14
OLS
-0.14
_ASC
-0.13
ẩn
-0.13
POSITIVE LOGITS
moth
0.32
mary
0.20
zers
0.19
มà¸Ń
0.18
mo
0.18
oud
0.18
mam
0.17
bers
0.16
dou
0.16
tle
0.16
Activations Density 0.010%