INDEX
    Explanations

    emotions and physical interactions between characters

    New Auto-Interp
    Negative Logits
     synd
    -0.15
     cref
    -0.14
    pane
    -0.14
    ic
    -0.14
     resistance
    -0.14
     Resistance
    -0.14
    iene
    -0.14
    idian
    -0.13
    afi
    -0.13
    _firestore
    -0.13
    POSITIVE LOGITS
    мо
    0.17
    à¹Ģหà¸Ļ
    0.15
    ivo
    0.14
    orr
    0.14
    lla
    0.14
     Roose
    0.14
    /gui
    0.14
    617
    0.14
    립
    0.14
    abei
    0.13
    Act Density 0.486%

    No Known Activations