INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Laser
    -0.07
    ระเบ
    -0.06
     лаборатор
    -0.06
    Latitude
    -0.06
     slaughtered
    -0.06
     Crom
    -0.06
    841
    -0.06
     lever
    -0.06
    ctl
    -0.06
     scales
    -0.06
    POSITIVE LOGITS
     friends
    0.14
     friend
    0.14
     Friend
    0.12
     Friends
    0.11
     vriend
    0.10
     друж
    0.10
    Friends
    0.10
    Friend
    0.09
    friend
    0.09
     friendships
    0.09
    Act Density 0.034%

    No Known Activations