INDEX
    Explanations

    proper nouns, particularly names and places

    New Auto-Interp
    Negative Logits
    irus
    -0.15
    mittel
    -0.15
    ourt
    -0.14
    akis
    -0.14
     DIRECTORY
    -0.13
    xis
    -0.13
    éīĦ
    -0.13
    ίζει
    -0.13
    /logger
    -0.13
    manual
    -0.13
    POSITIVE LOGITS
    .monitor
    0.13
    ici
    0.13
     mand
    0.13
    ieux
    0.13
    elerik
    0.13
    ocene
    0.12
     option
    0.12
    co
    0.12
    eu
    0.12
    oyal
    0.12
    Act Density 0.149%

    No Known Activations