INDEX
Explanations
Japanese terms associated with video games, particularly related to a specific game or character
the mentions of a specific character, "Amiibo," from the "Animal Crossing" video game series
New Auto-Interp
Negative Logits
Conclusion
-0.69
ALE
-0.65
angle
-0.64
pent
-0.64
unnecess
-0.64
school
-0.63
Defin
-0.63
raped
-0.62
Hitchcock
-0.62
hedon
-0.61
POSITIVE LOGITS
ibo
1.46
pload
1.06
iliar
0.82
lette
0.80
ombat
0.76
Chat
0.76
lda
0.75
arre
0.74
herer
0.73
zos
0.72
Activations Density 0.015%