INDEX
    Explanations

    mentions of a specific character type or name from a fictional universe

    New Auto-Interp
    Negative Logits
     Pineda
    -0.50
    getDocument
    -0.47
    ooo
    -0.46
     Schmid
    -0.45
    osan
    -0.43
    coo
    -0.43
    -0.41
    wachsene
    -0.40
    oo
    -0.40
     Aoki
    -0.40
    POSITIVE LOGITS
    ait
    0.76
    ais
    0.69
     Ai
    0.69
    ail
    0.68
    AIL
    0.65
     AIN
    0.63
     Aim
    0.63
    Ai
    0.62
     CreateTagHelper
    0.62
    raim
    0.61
    Act Density 0.058%

    No Known Activations