INDEX
    Explanations

    references to the ingredient butter in various contexts

    New Auto-Interp
    Negative Logits
    imit
    -0.15
       
    -0.15
    esta
    -0.15
    arts
    -0.15
    ament
    -0.14
     firm
    -0.14
    otec
    -0.14
    naments
    -0.14
    ote
    -0.13
    Cs
    -0.13
    POSITIVE LOGITS
    ordum
    0.18
    iglia
    0.17
    onya
    0.17
    .mybatisplus
    0.15
    acier
    0.15
    tember
    0.15
    dress
    0.15
    recated
    0.15
    GetType
    0.15
     dress
    0.15
    Act Density 0.005%

    No Known Activations