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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ttle
    -0.72
    rad
    -0.69
    aspx
    -0.69
    ovy
    -0.69
    gay
    -0.68
    ilan
    -0.67
    row
    -0.66
    aviour
    -0.66
    enery
    -0.65
    bos
    -0.65
    POSITIVE LOGITS
     fingerprints
    0.76
     ceilings
    0.72
     Sonia
    0.64
    aughs
    0.62
    ãĤª
    0.61
     motivations
    0.61
    ascript
    0.61
     chip
    0.60
     actionGroup
    0.60
     handwritten
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.