INDEX
    Explanations

    occurrences of the letter "s" in various contexts

    New Auto-Interp
    Negative Logits
    tas
    -0.17
    tones
    -0.17
    erv
    -0.17
    ts
    -0.17
    tem
    -0.17
    м
    -0.17
    aved
    -0.16
    unami
    -0.16
    olver
    -0.16
    ound
    -0.16
    POSITIVE LOGITS
     tart
    0.17
    child
    0.17
    cc
    0.16
    ot
    0.16
     mall
    0.16
    ere
    0.16
     junk
    0.16
    alk
    0.15
     mart
    0.15
    prog
    0.15
    Act Density 0.159%

    No Known Activations