INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     июля
    -0.87
    ших
    -0.83
    FlatAppearance
    -0.81
     mounds
    -0.81
    -0.77
     sculpting
    -0.77
    Structures
    -0.75
     handheld
    -0.74
     slutet
    -0.74
    vestream
    -0.73
    POSITIVE LOGITS
     wall
    2.84
     hanging
    2.48
     hung
    2.47
    hung
    2.28
     framed
    2.25
    wall
    2.19
     hangs
    2.08
    Hanging
    2.02
     hang
    2.02
     hanged
    1.98
    Act Density 0.037%

    No Known Activations