INDEX
    Explanations

    words related to family relationships and personal connections

    New Auto-Interp
    Negative Logits
     fathers
    -1.27
     Fathers
    -1.16
     grandson
    -1.13
    Daughter
    -1.13
    daughters
    -1.12
     grandsons
    -1.12
    fathers
    -1.11
     grandchildren
    -1.10
     Parent
    -1.10
     daughters
    -1.09
    POSITIVE LOGITS
     folks
    0.44
    UnitTesting
    0.43
     biological
    0.40
     ste
    0.39
    новништво
    0.39
     step
    0.36
     da
    0.35
    ICIAS
    0.34
     Biological
    0.34
     mergeFrom
    0.34
    Act Density 0.223%

    No Known Activations