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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Pä
    0.94
     বিষয়ক
    0.80
     insbesondere
    0.76
     раздел
    0.75
    ga
    0.75
     явля
    0.75
     zejména
    0.73
     Perkenalkan
    0.72
     duże
    0.72
    lope
    0.72
    POSITIVE LOGITS
    }=\
    0.76
     multitasking
    0.71
     worrying
    0.71
     Emperor
    0.70
    ين
    0.70
     fooling
    0.70
    Sister
    0.67
    }=
    0.66
    }_{
    0.66
     happy
    0.66
    Act Density 0.004%

    No Known Activations