INDEX
    Explanations

    expressions of disappointment in experiences, particularly regarding media and entertainment

    New Auto-Interp
    Negative Logits
    isp
    -0.16
     Klopp
    -0.15
    utron
    -0.15
     stuff
    -0.14
    iff
    -0.14
    aman
    -0.14
    ikan
    -0.14
    eldorf
    -0.14
    ynes
    -0.14
    λοÏħ
    -0.13
    POSITIVE LOGITS
    oven
    0.17
    avanaugh
    0.17
     xo
    0.15
     Reign
    0.14
    æĨ
    0.14
    838
    0.14
    caffe
    0.14
    ãģijãĤĮãģ©
    0.14
    ÛĮÙĦÛĮ
    0.13
    iasi
    0.13
    Act Density 0.235%

    No Known Activations