INDEX
    Explanations

    mentions of the word "mother."

    references to the concept of "mother."

    New Auto-Interp
    Negative Logits
     Flavoring
    -0.90
    raviolet
    -0.79
    EY
    -0.77
    ickr
    -0.75
    okers
    -0.74
    jriwal
    -0.71
    NRS
    -0.69
    urat
    -0.68
    EStreamFrame
    -0.67
    idian
    -0.66
    POSITIVE LOGITS
    hood
    1.19
    hesis
    1.08
    heses
    1.00
    ship
    0.96
    mother
    0.95
    hetical
    0.87
    hetically
    0.87
    wife
    0.84
    load
    0.84
    ships
    0.82
    Act Density 0.022%

    No Known Activations