INDEX
    Explanations

    book titles and authors

    New Auto-Interp
    Negative Logits
    İZ
    0.61
     victimization
    0.59
     Beyonce
    0.55
     Swarovski
    0.55
    odynam
    0.55
     manquer
    0.55
     tzw
    0.55
     норм
    0.54
    órios
    0.53
     dalamnya
    0.53
    POSITIVE LOGITS
    <unused2182>
    0.79
    т
    0.78
    <unused626>
    0.77
    <unused399>
    0.77
    <unused256>
    0.76
    <unused522>
    0.76
    <unused530>
    0.76
    <unused574>
    0.76
    <unused428>
    0.75
    <unused235>
    0.75
    Act Density 0.000%

    No Known Activations