INDEX
    Explanations

    emotional expressions of affection or attachment

    New Auto-Interp
    Negative Logits
    udo
    -0.16
     FactoryBot
    -0.15
    558
    -0.15
    vens
    -0.14
    /goto
    -0.14
    éal
    -0.14
    éis
    -0.14
    mos
    -0.14
    ãĤĤãģ£ãģ¨
    -0.13
    ربÙĩ
    -0.13
    POSITIVE LOGITS
     exception
    0.18
     Exceptions
    0.18
     exceptions
    0.18
     certain
    0.16
    UCK
    0.15
     Luc
    0.15
     Platt
    0.15
    кав
    0.14
     Ont
    0.14
    /Application
    0.14
    Act Density 0.088%

    No Known Activations