INDEX
Explanations
references to flowers and their significance as gifts
New Auto-Interp
Negative Logits
stew
-0.16
berger
-0.16
coat
-0.15
æŃ©
-0.15
ovol
-0.15
.erb
-0.14
alli
-0.14
addChild
-0.14
dress
-0.14
burger
-0.14
POSITIVE LOGITS
gift
0.36
gifts
0.35
gift
0.32
Gift
0.31
Gifts
0.30
Gift
0.29
éĢģ
0.21
_gift
0.21
éĢģ
0.20
gif
0.20
Activations Density 0.155%