INDEX
    Explanations

    instances of the word "but."

    New Auto-Interp
    Negative Logits
    äge
    -0.17
    elow
    -0.16
    -ÑĤо
    -0.16
    jee
    -0.16
    aggi
    -0.15
    776
    -0.14
    eÄį
    -0.14
    .dw
    -0.14
    VERR
    -0.14
    eko
    -0.14
    POSITIVE LOGITS
    opot
    0.15
     Dut
    0.15
    iface
    0.14
    è¿ĺæľī
    0.14
    imas
    0.14
    isky
    0.13
    RenderingContext
    0.13
    eyen
    0.13
    åįı
    0.13
    izen
    0.13
    Act Density 0.017%

    No Known Activations