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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    itie
    0.47
    </i>
    0.45
    enge
    0.45
    น
    0.43
    Passenger
    0.42
    paper
    0.41
    mis
    0.41
    Passengers
    0.41
    ignez
    0.41
    ignal
    0.40
    POSITIVE LOGITS
     використа
    0.46
     elér
    0.46
    一共
    0.45
    어
    0.45
     पार
    0.45
     institute
    0.45
     hubo
    0.45
    ৩৮
    0.44
    大约
    0.44
     ulaş
    0.44
    Act Density 0.006%

    No Known Activations