INDEX
    Explanations

    occurrences of specific author names

    New Auto-Interp
    Negative Logits
    MBED
    -0.15
    RIPT
    -0.14
     conform
    -0.14
    Winner
    -0.13
    å°ij女
    -0.13
    ovel
    -0.13
     Husband
    -0.13
    ckett
    -0.13
    rei
    -0.13
     Beste
    -0.13
    POSITIVE LOGITS
    çĦ
    0.15
    icine
    0.14
    oulouse
    0.14
    ikk
    0.14
     Usa
    0.14
     Mour
    0.13
    ãģ°ãģĭãĤĬ
    0.13
    íĸ¥
    0.13
    elt
    0.13
    ̧
    0.13
    Act Density 0.002%

    No Known Activations