INDEX
    Explanations

    references to family and relationships, particularly focusing on the term "son."

    New Auto-Interp
    Negative Logits
    ekk
    -0.15
    kie
    -0.15
     Farm
    -0.15
    ÑĨен
    -0.14
    anson
    -0.14
    uar
    -0.14
    enberg
    -0.14
     Fly
    -0.14
    iets
    -0.14
    Ë
    -0.14
    POSITIVE LOGITS
    riba
    0.16
    .apps
    0.15
    oron
    0.15
    ãĥ³ãĥī
    0.15
    eba
    0.14
     ÙħÙĤر
    0.14
    alaria
    0.14
    .glob
    0.14
    748
    0.14
    _force
    0.14
    Act Density 0.006%

    No Known Activations