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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sabbath
    -0.73
    WAR
    -0.72
    Sov
    -0.72
    phabet
    -0.71
    zai
    -0.70
    MJ
    -0.65
     Schwar
    -0.63
     Lutheran
    -0.62
    Lay
    -0.62
    cellaneous
    -0.61
    POSITIVE LOGITS
    obyl
    0.92
    onse
    0.86
    arbon
    0.74
    OA
    0.71
    starter
    0.70
    ometers
    0.70
     headlights
    0.69
    schild
    0.68
    oÄŁ
    0.66
    onga
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.