INDEX
    Explanations

    apprentice/apprenticeship

    New Auto-Interp
    Negative Logits
    on
    1.06
    ма
    1.02
     apari
    0.86
    f
    0.86
    om
    0.83
    ing
    0.73
     tamu
    0.73
     colle
    0.71
     snowy
    0.71
     the
    0.71
    POSITIVE LOGITS
     Apprentices
    1.25
     apprentices
    1.16
     apprenticeship
    1.02
    rentices
    1.00
    apprent
    0.98
     Apprentice
    0.86
     apprent
    0.83
    ors
    0.81
     apprentice
    0.78
    ür
    0.78
    Act Density 0.007%

    No Known Activations