INDEX
    Explanations

    instances of the word "Man"

    New Auto-Interp
    Negative Logits
    dni
    -0.16
    ãģ£ãģı
    -0.15
    verty
    -0.14
    rette
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    isse
    -0.14
    entiful
    -0.14
    iano
    -0.14
    .sourceforge
    -0.13
    导èĩ´
    -0.13
    POSITIVE LOGITS
    akov
    0.17
    bond
    0.16
     bond
    0.16
     bonding
    0.15
    urd
    0.15
    pig
    0.15
    linger
    0.14
     Reco
    0.14
    _launcher
    0.14
    ector
    0.14
    Act Density 0.011%

    No Known Activations