INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     amfani
    -0.09
     tse
    -0.08
     Wil
    -0.08
    altungs
    -0.08
     tapauks
    -0.08
     pož
    -0.08
     Nik
    -0.08
     Musiker
    -0.08
     nzira
    -0.08
     داسې
    -0.08
    POSITIVE LOGITS
     society
    0.08
     readability
    0.08
     ghost
    0.08
     innocent
    0.08
     infra
    0.07
    GM
    0.07
    ghost
    0.07
     stability
    0.07
     lifecycle
    0.07
    ced
    0.07
    Act Density 0.057%

    No Known Activations