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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    roma
    -0.77
    oba
    -0.66
    obin
    -0.66
     Oversight
    -0.65
    osate
    -0.64
    atism
    -0.64
    ilege
    -0.64
    onomy
    -0.64
    uly
    -0.63
     Powder
    -0.63
    POSITIVE LOGITS
    hower
    0.81
     Username
    0.70
     unsuccessfully
    0.69
    enegger
    0.64
    wikipedia
    0.63
    Downloadha
    0.61
     sten
    0.61
     nurse
    0.60
     glac
    0.59
     goodbye
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.