INDEX
    Explanations

    terms related to mathematics and mathematical concepts

    New Auto-Interp
    Negative Logits
     Jefus
    -1.01
    -------
    -1.00
     myſelf
    -0.95
     themſelves
    -0.90
    Geplaatst
    -0.90
    JsonPropertyName
    -0.89
     AssemblyCompany
    -0.88
     becauſe
    -0.87
    windowFixed
    -0.87
    Personensuche
    -0.86
    POSITIVE LOGITS
     Mathis
    1.51
     MATH
    1.34
     Math
    1.30
     math
    1.26
    math
    1.25
    MATH
    1.20
    Math
    1.16
     Mathilde
    0.94
     mathematics
    0.94
    Mathematics
    0.93
    Act Density 0.130%

    No Known Activations