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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    paces
    -0.79
    pherd
    -0.77
    ensor
    -0.75
    course
    -0.72
    poon
    -0.71
    utterstock
    -0.71
    arters
    -0.71
    know
    -0.70
    pring
    -0.70
    creen
    -0.69
    POSITIVE LOGITS
    asio
    0.79
     Suzuki
    0.79
     Ivan
    0.69
    OPA
    0.66
     Castro
    0.64
    ECD
    0.62
     Gonzalez
    0.61
     Hughes
    0.59
     Hernandez
    0.59
     boost
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.