INDEX
    Explanations

    references to kitchen appliances and their features

    New Auto-Interp
    Negative Logits
    Disp
    -0.17
    lez
    -0.17
    ãĥ£
    -0.16
    á»§y
    -0.15
    ufs
    -0.15
    گاÙĨ
    -0.15
     Disp
    -0.15
    disp
    -0.15
    sing
    -0.14
    ura
    -0.14
    POSITIVE LOGITS
    ette
    0.21
    /lab
    0.19
    ettes
    0.18
    maid
    0.18
    /gallery
    0.17
    /shop
    0.17
    enze
    0.15
    ounty
    0.15
    ney
    0.15
    walls
    0.15
    Act Density 0.033%

    No Known Activations