INDEX
    Explanations

    mentions of names and initials associated with prominent individuals

    New Auto-Interp
    Negative Logits
    lsru
    -0.17
     mate
    -0.14
    zu
    -0.14
    RITE
    -0.14
    ENTA
    -0.14
    esting
    -0.14
    opis
    -0.14
    ÙĦØŃ
    -0.14
    scope
    -0.14
    abe
    -0.13
    POSITIVE LOGITS
    morgan
    0.19
     Morgan
    0.18
     Getty
    0.17
    gart
    0.16
    otts
    0.16
     Morg
    0.16
     Sous
    0.15
    Texto
    0.15
    gan
    0.15
    ì¼ĵ
    0.14
    Act Density 0.008%

    No Known Activations