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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     antioxid
    -0.70
     posit
    -0.65
     ultras
    -0.65
     inputs
    -0.64
     eas
    -0.63
    Ly
    -0.63
    :\
    -0.62
     pregn
    -0.61
    Pic
    -0.61
    uno
    -0.61
    POSITIVE LOGITS
    edia
    1.01
    urities
    0.82
    ashington
    0.76
     Minotaur
    0.74
    rencies
    0.71
    eanor
    0.68
    apego
    0.67
     Daylight
    0.67
    verning
    0.67
    leck
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.