INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ç§©åºı
    -0.32
    åijķ
    -0.27
    preview
    -0.26
    andi
    -0.26
    hover
    -0.26
    undo
    -0.26
    ij
    -0.26
    Condition
    -0.26
    ownload
    -0.25
    iali
    -0.25
    POSITIVE LOGITS
     po
    0.31
     ingredients
    0.30
     tray
    0.28
     ingredient
    0.28
     recipes
    0.26
     redis
    0.26
     pur
    0.25
     mis
    0.25
     cons
    0.25
     Po
    0.25
    Act Density 0.037%

    No Known Activations