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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ogh
    -0.83
    oran
    -0.73
    emi
    -0.70
    eers
    -0.69
    ury
    -0.69
    uates
    -0.67
    ptin
    -0.67
    uku
    -0.66
    anos
    -0.66
    adier
    -0.66
    POSITIVE LOGITS
    ESA
    0.68
    mining
    0.67
     HRC
    0.65
    ï¸ı
    0.65
     AVG
    0.65
     Guerrero
    0.65
    fecture
    0.64
    yna
    0.63
     singer
    0.62
     Floyd
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.