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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     inappropriés
    -0.91
    gier
    -0.87
    mitsubishi
    -0.87
    ált
    -0.87
    brink
    -0.86
     risk
    -0.85
    的美
    -0.84
    getIcon
    -0.84
    าส
    -0.84
    iken
    -0.84
    POSITIVE LOGITS
    婓
    0.96
     indik
    0.92
    DALE
    0.91
    ~~~~~~~~~~~~~~~~
    0.90
     their
    0.90
     minn
    0.90
     captur
    0.88
     néanmoins
    0.88
     Direktor
    0.88
     raste
    0.87
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.