INDEX
    Explanations

    names of authors and contributors in academic publications

    New Auto-Interp
    Negative Logits
    osaur
    -0.15
    rych
    -0.15
    otton
    -0.15
    ophil
    -0.14
    rench
    -0.14
    olta
    -0.13
    оÑĢаÑı
    -0.13
    oru
    -0.13
    olian
    -0.13
    alary
    -0.13
    POSITIVE LOGITS
    abs
    0.14
    izo
    0.14
    utt
    0.13
    Peripheral
    0.13
    iz
    0.13
    oad
    0.13
    iza
    0.13
     Mandal
    0.13
    adel
    0.13
    ĵ
    0.13
    Act Density 0.058%

    No Known Activations