INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sofre
    -0.08
    raî
    -0.08
     militar
    -0.08
     héro
    -0.07
     filmu
    -0.07
    -0.07
     UIImage
    -0.07
     neural
    -0.07
    гы
    -0.07
    xff
    -0.07
    POSITIVE LOGITS
     TCL
    0.09
    .goto
    0.08
    _commands
    0.08
     Tcl
    0.08
    (commands
    0.08
    (cmd
    0.08
    0.08
    zia
    0.08
    .what
    0.08
    0.08
    Act Density 0.002%

    No Known Activations