INDEX
    Explanations

    phrases related to art and creativity

    New Auto-Interp
    Negative Logits
     when
    -0.31
    _when
    -0.26
    when
    -0.26
     quando
    -0.24
    When
    -0.24
     когда
    -0.23
     When
    -0.23
     cuando
    -0.22
     khi
    -0.22
     à¤ľà¤¬
    -0.21
    POSITIVE LOGITS
     instead
    0.22
     it
    0.21
    instead
    0.20
     вмеÑģÑĤ
    0.19
    ï¼Įå®ĥ
    0.18
     chances
    0.17
     expecting
    0.17
     there
    0.17
     itu
    0.16
     everything
    0.16
    Act Density 0.170%

    No Known Activations