INDEX
Explanations
references to specific individuals and their connections to Japanese culture or media
New Auto-Interp
Negative Logits
ymb
-0.18
_handling
-0.17
alg
-0.17
Nah
-0.15
æĴŃ
-0.15
ymm
-0.15
_lifetime
-0.14
Wheat
-0.14
/lg
-0.14
mah
-0.14
POSITIVE LOGITS
aki
0.26
aku
0.26
ui
0.24
uke
0.24
ai
0.24
uo
0.23
uien
0.22
u
0.20
eson
0.20
oku
0.20
Activations Density 0.048%