INDEX
    Explanations

    references to cutting or cuts in various contexts

    New Auto-Interp
    Negative Logits
    oles
    -0.18
    oin
    -0.18
    hire
    -0.17
    esk
    -0.16
    EMENT
    -0.16
    als
    -0.16
    es
    -0.15
    636
    -0.15
    czy
    -0.15
    ated
    -0.15
    POSITIVE LOGITS
    tings
    0.35
    aneous
    0.33
    ting
    0.30
    cut
    0.30
    -cut
    0.28
    throat
    0.28
    =cut
    0.28
    .cut
    0.27
    ters
    0.27
     Cut
    0.24
    Act Density 0.031%

    No Known Activations