INDEX
    Explanations

    suffix ious/ous/orous

    New Auto-Interp
    Negative Logits
    l
    -0.07
     никто
    -0.07
     Merlin
    -0.07
     rl
    -0.07
    .MAX
    -0.07
    te
    -0.07
    _xt
    -0.07
     nobody
    -0.07
     deter
    -0.07
    _iter
    -0.07
    POSITIVE LOGITS
    US
    0.11
    ious
    0.10
    ous
    0.10
    us
    0.09
    antis
    0.08
    BUS
    0.08
    ου
    0.08
    LESS
    0.08
    ius
    0.08
    IOUS
    0.08
    Act Density 0.065%

    No Known Activations