INDEX
    Explanations

    expressions of enthusiasm and admiration

    New Auto-Interp
    Negative Logits
    ánu
    -0.20
    ลาà¸Ķ
    -0.16
     Roberts
    -0.15
    ahas
    -0.14
    echa
    -0.14
    اÙĦÙĬ
    -0.14
     çĤ
    -0.14
    ĥĿ
    -0.14
    /lang
    -0.14
    iosper
    -0.14
    POSITIVE LOGITS
    nic
    0.16
     Nice
    0.15
    uko
    0.15
     MOUSE
    0.14
     nic
    0.14
    aran
    0.14
    azi
    0.14
    remely
    0.14
     Masc
    0.14
    imal
    0.14
    Act Density 0.010%

    No Known Activations