INDEX
    Explanations

    mentions of the city Boston

    New Auto-Interp
    Negative Logits
     Boston
    -1.85
    Boston
    -1.71
     boston
    -1.56
     BOSTON
    -1.55
    boston
    -1.36
    BOSTON
    -1.35
     Bost
    -0.91
     Massachusetts
    -0.72
    Massachusetts
    -0.69
     Philadelphia
    -0.67
    POSITIVE LOGITS
    zepte
    0.37
    CppCodeGen
    0.35
    künfte
    0.35
    neté
    0.35
    ThroughAttribute
    0.34
    Esper
    0.34
     Aes
    0.34
    chaffung
    0.34
    WHEREAS
    0.33
     fédé
    0.33
    Act Density 0.002%

    No Known Activations