INDEX
    Explanations

    mentions of the city of Venice and related terms

    New Auto-Interp
    Negative Logits
    agn
    -0.18
    rubu
    -0.17
    iffies
    -0.15
    clarations
    -0.15
    buie
    -0.15
    uhn
    -0.15
    ahtar
    -0.14
    TOTYPE
    -0.14
    letcher
    -0.14
    uckle
    -0.14
    POSITIVE LOGITS
    ereal
    0.27
    ues
    0.26
    eto
    0.23
    ables
    0.23
    ice
    0.22
    itian
    0.22
    kat
    0.22
    ison
    0.22
    et
    0.21
    egas
    0.20
    Act Density 0.011%

    No Known Activations