INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    amee
    -0.08
     homem
    -0.08
     Tmp
    -0.07
     Emil
    -0.07
     FW
    -0.07
     всі
    -0.07
     ons
    -0.07
     Thomas
    -0.07
     Gtk
    -0.07
    foreground
    -0.07
    POSITIVE LOGITS
    o
    0.10
     bottles
    0.08
     conversation
    0.08
    ordinary
    0.08
     bottle
    0.08
    baarheid
    0.07
     diode
    0.07
    achd
    0.07
     wei
    0.07
    IANT
    0.07
    Act Density 0.006%

    No Known Activations