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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Recipe
    -0.77
    20439
    -0.76
     Flavoring
    -0.73
     [&
    -0.67
    Against
    -0.64
    erie
    -0.63
    Reviewer
    -0.61
     invited
    -0.60
    Ingredients
    -0.59
     wrench
    -0.59
    POSITIVE LOGITS
    lling
    0.79
    reditary
    0.70
     Viz
    0.69
    Downloadha
    0.68
    Va
    0.67
     Rico
    0.67
     AAA
    0.66
     Cheong
    0.65
    ugu
    0.63
    olulu
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.