INDEX
    Explanations

    mentions of high-profile individuals and corporations

    New Auto-Interp
    Negative Logits
     Vordergrund
    -0.77
     photolibrary
    -0.72
    éphane
    -0.72
    hésite
    -0.67
    ceptre
    -0.65
     Serr
    -0.64
    ÉM
    -0.64
    Bronnen
    -0.63
    esterday
    -0.62
    ſſer
    -0.61
    POSITIVE LOGITS
    riwal
    0.84
    dymyr
    0.76
    LookAnd
    0.70
    okovic
    0.68
    ttino
    0.67
    anyahu
    0.66
     Obrador
    0.66
    featureID
    0.65
    Ronaldo
    0.65
     Messi
    0.65
    Act Density 0.438%

    No Known Activations