INDEX
    Explanations

    cases of "access" and related words like "accessible" or "easier access"

    New Auto-Interp
    Negative Logits
     itſelf
    -1.55
     myſelf
    -1.50
     Efq
    -1.46
     Theſe
    -1.39
     propOrder
    -1.37
     Shakspeare
    -1.34
     ་་
    -1.34
     Monfieur
    -1.30
     Jefus
    -1.29
     ſeveral
    -1.28
    POSITIVE LOGITS
     is
    0.77
    0.75
    .
    0.72
     in
    0.67
     from
    0.65
     on
    0.63
     '
    0.62
    ,
    0.62
     I
    0.61
    ;
    0.61
    Act Density 1.508%

    No Known Activations