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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Liberties
    -0.68
     Badge
    -0.66
    tained
    -0.64
     Charm
    -0.62
    iles
    -0.62
     Arc
    -0.61
    slaught
    -0.60
     Files
    -0.60
    SEA
    -0.60
     compatible
    -0.59
    POSITIVE LOGITS
    aretz
    0.73
    stocks
    0.71
    catentry
    0.67
    Xi
    0.67
     embod
    0.66
     tasting
    0.66
    Output
    0.64
     Kirin
    0.64
    otle
    0.64
     embodiment
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.