INDEX
    Explanations

    the word "going" in various contexts

    New Auto-Interp
    Negative Logits
    quire
    -0.20
    æħİ
    -0.14
    CHANT
    -0.14
    icerca
    -0.14
    amel
    -0.14
    ceso
    -0.14
    ÙĪÙĦا
    -0.14
    лÑıли
    -0.14
    azu
    -0.14
    /remove
    -0.14
    POSITIVE LOGITS
     nowhere
    0.24
     ot
    0.21
    onna
    0.20
     be
    0.18
    ING
    0.18
     places
    0.17
     shopping
    0.17
     gonna
    0.17
     somewhere
    0.17
    gon
    0.16
    Act Density 0.030%

    No Known Activations