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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tro
    -0.80
     membership
    -0.77
     arte
    -0.69
     amen
    -0.68
    ization
    -0.67
     patronage
    -0.65
    isation
    -0.64
     annexation
    -0.64
     Corona
    -0.64
    riages
    -0.63
    POSITIVE LOGITS
    erm
    0.66
    adelphia
    0.66
    anim
    0.65
    rou
    0.65
    inois
    0.64
    lan
    0.64
    ouri
    0.63
    leon
    0.63
    Offline
    0.63
    aned
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.