INDEX
    Explanations

    instances of yelling or shouting

    New Auto-Interp
    Negative Logits
    ops
    -0.14
    zik
    -0.14
    ugh
    -0.14
    ppard
    -0.14
     ling
    -0.14
    ust
    -0.14
    IGHL
    -0.14
    åIJĽ
    -0.13
    MOTE
    -0.13
    FORCE
    -0.13
    POSITIVE LOGITS
    æľĭ
    0.17
     Vak
    0.16
    lesc
    0.16
    861
    0.15
     ho
    0.15
    urette
    0.14
    ichel
    0.14
    atis
    0.14
    à¤Ĥस
    0.14
    venes
    0.14
    Act Density 0.053%

    No Known Activations