INDEX
    Explanations

    expressions of strong emotional states

    New Auto-Interp
    Negative Logits
    avior
    -0.72
    -0.71
    }}}
    -0.66
    oldown
    -0.66
    ドラ
    -0.65
    Export
    -0.64
    aviour
    -0.63
    ��
    -0.63
     overshadow
    -0.63
    -0.62
    POSITIVE LOGITS
     thankful
    0.99
     grateful
    0.98
     glad
    0.96
     impressed
    0.93
     thrilled
    0.93
     pleased
    0.93
     saddened
    0.90
     delighted
    0.90
     sorry
    0.89
     proud
    0.89
    Act Density 0.091%

    No Known Activations