INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Trou
    1.19
     mort
    1.17
     McDon
    1.16
     Bow
    1.13
     Nut
    1.11
     CAB
    1.11
    密码
    1.11
     Dunham
    1.10
     nut
    1.10
    mort
    1.07
    POSITIVE LOGITS
    i
    1.49
     i
    1.33
    ii
    0.95
    afi
    0.93
    mii
    0.92
    𝑖
    0.89
    ieri
    0.88
     Jai
    0.88
    0.87
    Jai
    0.82
    Act Density 0.222%

    No Known Activations