INDEX
    Explanations

    names that start with "Roy" or "Joy."

    New Auto-Interp
    Negative Logits
    äºĭ
    -0.19
    p
    -0.17
    imer
    -0.17
    pie
    -0.16
    ext
    -0.16
    pri
    -0.16
    pit
    -0.16
    sto
    -0.15
    sy
    -0.15
    store
    -0.15
    POSITIVE LOGITS
    ssa
    0.19
    enne
    0.18
    sson
    0.18
    ne
    0.18
    ÚĺÙĩ
    0.17
    alty
    0.17
    ÌĪ
    0.17
    rides
    0.17
    alties
    0.17
    olland
    0.17
    Act Density 0.085%

    No Known Activations