INDEX
    Explanations

    possessive pronouns and expressions of ownership

    New Auto-Interp
    Negative Logits
    owo
    -0.16
    onde
    -0.15
    arium
    -0.15
    antha
    -0.15
    ÃŁ
    -0.15
    oubted
    -0.14
    eki
    -0.14
    kening
    -0.13
     ÑĢобоÑĤÑĥ
    -0.13
    uron
    -0.13
    POSITIVE LOGITS
    shal
    0.17
     own
    0.16
     Glover
    0.15
    iggs
    0.14
    361
    0.14
    олÑİ
    0.14
    .overflow
    0.14
    613
    0.13
    izi
    0.13
    isson
    0.13
    Act Density 0.110%

    No Known Activations