INDEX
    Explanations

    mentions of specific individuals, particularly those with the last names Peters or Cousins

    New Auto-Interp
    Negative Logits
    izen
    -0.80
    TPS
    -0.75
    ocking
    -0.67
    ************
    -0.67
    icity
    -0.66
    iversity
    -0.63
    EMBER
    -0.62
    è¦ļéĨĴ
    -0.61
    VIDIA
    -0.61
    isse
    -0.61
    POSITIVE LOGITS
     Cousins
    0.95
    ername
    0.80
    opher
    0.80
    gaard
    0.79
    kus
    0.77
    hus
    0.77
    workshop
    0.76
    chal
    0.75
    bats
    0.74
    ystem
    0.72
    Act Density 0.020%

    No Known Activations