INDEX
    Explanations

    contact information and online presence details

    New Auto-Interp
    Negative Logits
     ourselves
    -0.17
     ours
    -0.15
    ours
    -0.15
    oring
    -0.14
    ãģİ
    -0.14
    ify
    -0.13
    kins
    -0.13
    ax
    -0.13
    489
    -0.13
     ballo
    -0.13
    POSITIVE LOGITS
     follow
    0.28
     Follow
    0.28
    Follow
    0.27
    follow
    0.26
     Reach
    0.22
     reach
    0.21
    contact
    0.21
     contact
    0.21
     follower
    0.20
     twitter
    0.20
    Act Density 0.034%

    No Known Activations