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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    OFF
    -0.66
     Fitzgerald
    -0.63
     Owens
    -0.63
     Cheong
    -0.63
     Sole
    -0.63
     Bryant
    -0.62
     Wiley
    -0.62
    through
    -0.61
     Pipe
    -0.61
     Meter
    -0.61
    POSITIVE LOGITS
    iced
    0.80
    iberal
    0.79
    icism
    0.77
     partName
    0.75
    ourage
    0.75
    icing
    0.74
    axies
    0.74
    etheus
    0.73
    itably
    0.72
    atural
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.