INDEX
    Explanations

    technical specifications and version information

    New Auto-Interp
    Negative Logits
    illi
    -0.16
    iju
    -0.15
    pollo
    -0.15
    _ARB
    -0.15
    ETERS
    -0.14
    656
    -0.14
     Mai
    -0.14
    èĹ
    -0.14
     techno
    -0.14
    ánu
    -0.14
    POSITIVE LOGITS
     plain
    0.17
    bag
    0.16
     manually
    0.16
    rum
    0.15
    avr
    0.15
     trif
    0.14
     Plain
    0.14
    um
    0.14
     Isles
    0.14
    Plain
    0.14
    Act Density 0.286%

    No Known Activations