INDEX
    Explanations

    references to familial relationships, particularly focusing on mothers and fathers

    New Auto-Interp
    Negative Logits
     itself
    -0.20
     granddaughter
    -0.17
     grandson
    -0.15
     Computing
    -0.14
     son
    -0.14
     daughter
    -0.14
    WARE
    -0.14
    Stamp
    -0.14
    ATUS
    -0.14
    ROME
    -0.14
    POSITIVE LOGITS
    大人
    0.20
    /legal
    0.19
    /gr
    0.17
    ially
    0.16
    arily
    0.16
    ÄĽst
    0.15
    -in
    0.15
    ents
    0.15
     remar
    0.15
    lessness
    0.15
    Act Density 0.069%

    No Known Activations