INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    itamin
    -0.07
     Dark
    -0.07
    <TextView
    -0.07
    Aff
    -0.06
     challeng
    -0.06
     specialize
    -0.06
     heterosexual
    -0.06
     respectful
    -0.06
     mattered
    -0.06
    	pos
    -0.06
    POSITIVE LOGITS
     spontaneous
    0.09
     spontaneously
    0.08
    break
    0.07
    ClassNotFoundException
    0.07
    startTime
    0.07
    AlgorithmException
    0.07
    =_('
    0.06
     контролю
    0.06
    respuesta
    0.06
     напри
    0.06
    Act Density 0.004%

    No Known Activations