INDEX
    Explanations

    future actions and intentions

    New Auto-Interp
    Negative Logits
     dangling
    0.84
    ComponentScan
    0.77
     expressing
    0.77
    0.77
     Motto
    0.75
     majoring
    0.72
    Setting
    0.71
     belonging
    0.71
     leaking
    0.71
     Relating
    0.71
    POSITIVE LOGITS
     gonna
    1.12
    ly
    1.09
     Gonna
    0.94
    𝗲
    0.89
    мулятор
    0.84
    LY
    0.84
    0.82
    ोली
    0.81
     phải
    0.80
    theless
    0.79
    Act Density 0.014%

    No Known Activations