INDEX
    Explanations

    Scandinavian characters and words

    characters or symbols, particularly special characters resembling letters or diacritics

    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.74
     Crus
    -0.71
    ORED
    -0.69
    IFIED
    -0.63
     Throne
    -0.61
    IONS
    -0.60
    ively
    -0.60
    arily
    -0.59
     kernels
    -0.58
    Beat
    -0.57
    POSITIVE LOGITS
    rd
    1.20
    rg
    1.17
    nda
    1.14
    rm
    1.12
    rn
    1.11
    ng
    1.06
    der
    1.02
    rent
    1.02
    dra
    1.01
    sta
    1.01
    Act Density 0.051%

    No Known Activations