INDEX
    Explanations

    the word "surrogate" or variations of it

    references to surrogates in various contexts

    New Auto-Interp
    Negative Logits
    inness
    -0.91
    INESS
    -0.84
    ulhu
    -0.75
    azes
    -0.73
    alach
    -0.72
    OA
    -0.70
    oak
    -0.70
    IST
    -0.70
    endon
    -0.69
    ovie
    -0.69
    POSITIVE LOGITS
     surrog
    1.58
     surrogate
    1.37
     Parenthood
    0.73
     gest
    0.73
    riages
    0.70
     laun
    0.69
    ãĤ§
    0.68
     encour
    0.67
     airst
    0.65
     lod
    0.64
    Act Density 0.007%

    No Known Activations