INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
     Fuj
    -0.08
    apsulation
    -0.08
     activated
    -0.07
     refugees
    -0.07
     obchod
    -0.07
     корист
    -0.07
     patches
    -0.07
    aptop
    -0.07
     cracker
    -0.07
    POSITIVE LOGITS
     Nu
    0.09
    Nu
    0.08
    主营
    0.08
     bisexual
    0.08
    след
    0.08
    _marks
    0.07
    dbo
    0.07
    0.07
    0.07
     Nip
    0.07
    Act Density 0.001%

    No Known Activations