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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xon
    -0.72
     Ples
    -0.70
     Continent
    -0.67
     Nationwide
    -0.64
     Preferences
    -0.63
    Sov
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.61
     WORLD
    -0.61
     Lans
    -0.61
     Argon
    -0.61
    POSITIVE LOGITS
    ienced
    0.79
    gur
    0.73
    afa
    0.71
    liness
    0.71
    ldon
    0.70
    "},{"
    0.69
    iencies
    0.68
    manship
    0.67
    istrate
    0.65
    imal
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.