INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .attribute
    -0.07
     enh
    -0.07
    comm
    -0.07
    _port
    -0.07
    boundary
    -0.07
    Transcript
    -0.07
    binary
    -0.07
    _attribute
    -0.07
     Binary
    -0.07
    iface
    -0.07
    POSITIVE LOGITS
     juvenil
    0.08
     mountainous
    0.08
     Karate
    0.08
     tur
    0.08
     Bhutan
    0.08
    0.08
     Hir
    0.07
     oliva
    0.07
     Kiel
    0.07
     buffalo
    0.07
    Act Density 0.000%

    No Known Activations