INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Temperature
    -0.68
    izoph
    -0.66
    Xi
    -0.64
     tourism
    -0.61
     Citiz
    -0.60
     Korra
    -0.58
     Siberia
    -0.58
    BIL
    -0.57
     ultras
    -0.57
     Europa
    -0.57
    POSITIVE LOGITS
     Jr
    1.29
    baum
    1.20
    meyer
    1.17
    berger
    1.16
    iewicz
    1.14
    baugh
    1.11
    owski
    1.11
    kamp
    1.10
    idge
    1.08
    hoff
    1.08
    Act Density 0.467%

    No Known Activations