INDEX
Explanations
mentions of the word "son" or related family terms indicating lineage or descent
New Auto-Interp
Negative Logits
tn
-0.16
ture
-0.16
tin
-0.15
uer
-0.15
overy
-0.15
ickerView
-0.14
uron
-0.14
olini
-0.14
engo
-0.14
coat
-0.14
POSITIVE LOGITS
nect
0.17
naire
0.17
ucle
0.16
WithDuration
0.15
ality
0.15
Ìĥ
0.15
ÙĥÙĩ
0.14
ne
0.14
WithName
0.13
nier
0.13
Activations Density 0.032%