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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Setiap
    0.76
     Wellbeing
    0.76
    2
    0.75
     Likewise
    0.73
     Når
    0.70
    3
    0.68
     Retreat
    0.68
                
    0.67
     Director
    0.67
     Therefore
    0.66
    POSITIVE LOGITS
    ى
    0.92
    álie
    0.88
    <unused64>
    0.82
    ıyordu
    0.82
     הר
    0.80
     interni
    0.79
    ্্
    0.79
     peruse
    0.79
    llll
    0.78
    uksi
    0.77
    Act Density 0.002%

    No Known Activations