INDEX
Explanations
references to specific family activities and experiences
New Auto-Interp
Negative Logits
granny
-0.17
readcr
-0.15
elters
-0.15
grandma
-0.14
ruc
-0.14
pivot
-0.14
ãĥijãĥ³
-0.14
Grandma
-0.14
poon
-0.13
â̦↵↵↵
-0.13
POSITIVE LOGITS
our
0.26
ourselves
0.26
ours
0.22
æĪij们çļĦ
0.20
notre
0.20
son
0.19
our
0.19
æĪijåĢij
0.19
nostro
0.19
nuestro
0.18
Activations Density 0.525%