INDEX
    Explanations

    words and phrases indicating a strong emotional response or intensity

    New Auto-Interp
    Negative Logits
    ehler
    -0.15
    strcasecmp
    -0.14
    çĬ¯
    -0.14
    fad
    -0.14
    724
    -0.14
    324
    -0.14
    물
    -0.14
    igi
    -0.14
    429
    -0.14
    ::*
    -0.14
    POSITIVE LOGITS
    ãĥ©ãĥĥãĤ¯
    0.16
    uada
    0.16
    iž
    0.15
    achel
    0.15
    ãĥķãĤ
    0.14
    bro
    0.14
    Bachelor
    0.14
    utm
    0.14
    reopen
    0.14
    eturn
    0.13
    Act Density 0.000%

    No Known Activations