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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.79
    TeX
    -0.77
    acio
    -0.72
    Aren
    -0.70
    é»Ĵ
    -0.69
     Tradable
    -0.69
    Ô
    -0.69
    姫
    -0.67
    rencies
    -0.67
    ORPG
    -0.66
    POSITIVE LOGITS
    alone
    0.66
     Metatron
    0.63
     Miranda
    0.62
    had
    0.60
     Martha
    0.59
    kar
    0.59
     cla
    0.58
    killer
    0.58
     Tanaka
    0.57
     Petraeus
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.