INDEX
    Explanations

    the phrase "Game of Thrones" in various forms and cases

    New Auto-Interp
    Negative Logits
    uze
    -0.18
    ownik
    -0.16
    aba
    -0.16
    kiye
    -0.15
    pton
    -0.15
    olv
    -0.14
    pta
    -0.14
    iland
    -0.14
     frank
    -0.14
    efore
    -0.14
    POSITIVE LOGITS
     Mothers
    0.17
    /fw
    0.15
     claim
    0.15
     Mother
    0.15
    èįī
    0.15
     simul
    0.14
     claims
    0.14
    simd
    0.14
     пÑĢод
    0.14
     life
    0.13
    Act Density 0.008%

    No Known Activations