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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     accur
    -0.73
    thening
    -0.70
     expended
    -0.69
     IOC
    -0.68
    omen
    -0.65
    tons
    -0.64
    gery
    -0.62
    ency
    -0.61
    imming
    -0.61
     ancest
    -0.61
    POSITIVE LOGITS
    âĸ¬
    0.87
    NER
    0.78
    CHECK
    0.70
    EMBER
    0.69
     Shade
    0.69
    iterator
    0.68
    OE
    0.67
    EV
    0.66
    emon
    0.66
    WIN
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.