INDEX
    Explanations

    concepts related to freedom of speech and political ideology

    New Auto-Interp
    Negative Logits
    ulkan
    -0.15
    ropoda
    -0.14
    UNCH
    -0.14
     upp
    -0.14
    anie
    -0.14
    elfare
    -0.14
     gent
    -0.14
    assen
    -0.14
     om
    -0.13
     Okay
    -0.13
    POSITIVE LOGITS
    argout
    0.16
    Ïħγ
    0.16
    .DOM
    0.15
    æŁĵ
    0.15
    _hdl
    0.15
    lex
    0.14
    vet
    0.14
    asil
    0.14
    ildo
    0.14
    InView
    0.13
    Act Density 0.248%

    No Known Activations