INDEX
    Explanations

    references to human rights and the concept of humanity

    New Auto-Interp
    Negative Logits
    INCT
    -0.16
    ulong
    -0.15
    yr
    -0.15
    gers
    -0.15
    Ìģ
    -0.15
    ional
    -0.15
    gi
    -0.15
    ingly
    -0.15
    inct
    -0.14
    iner
    -0.14
    POSITIVE LOGITS
    izing
    0.21
    ized
    0.21
    ization
    0.18
    oids
    0.18
    pire
    0.17
    IGHLIGHT
    0.17
    ifest
    0.16
    ugg
    0.16
    istic
    0.16
    isation
    0.16
    Act Density 0.042%

    No Known Activations