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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ulhu
    -0.77
    chwitz
    -0.76
    phas
    -0.73
    farious
    -0.71
    ipples
    -0.69
    ilitarian
    -0.69
     bothering
    -0.68
    ernaut
    -0.68
    oppable
    -0.67
    unker
    -0.65
    POSITIVE LOGITS
    ï¸ı
    0.87
    Ward
    0.74
    Privacy
    0.69
     confidentiality
    0.68
    esc
    0.67
     Lib
    0.67
     innocence
    0.67
     Juliet
    0.65
     CPC
    0.65
     BDS
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.