Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     EntryPoint
    -0.15
     Hust
    -0.15
     Strand
    -0.14
     Ole
    -0.14
     ("
    -0.13
    .RightToLeft
    -0.13
    oyal
    -0.13
     Advantage
    -0.13
     Parents
    -0.13
     tây
    -0.13
    POSITIVE LOGITS
    sez
    0.15
     ingredient
    0.14
     Engines
    0.14
     ingredients
    0.14
     Ingredients
    0.14
     Ingredient
    0.14
     Mattis
    0.14
    Sparse
    0.14
    otte
    0.13
    _seek
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.