INDEX
    Explanations

    mentions of educational institutions or related concepts

    New Auto-Interp
    Negative Logits
    \}_{
    -0.74
    picable
    -0.72
     Mante
    -0.71
     vivi
    -0.71
    ViewFeatures
    -0.70
    ANTED
    -0.70
    ourites
    -0.70
     Zuw
    -0.69
     المقد
    -0.69
    вяз
    -0.67
    POSITIVE LOGITS
     school
    1.74
     School
    1.65
    school
    1.63
    School
    1.58
     SCHOOL
    1.49
     schools
    1.45
    SCHOOL
    1.42
    chool
    1.39
     Schools
    1.29
    schools
    1.26
    Act Density 0.040%

    No Known Activations