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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     a
    0.91
     was
    0.82
    ございました
    0.82
     reverb
    0.77
     masterpiece
    0.76
    Alright
    0.76
     aconteceu
    0.76
    +
    0.75
     you
    0.74
    ست
    0.73
    POSITIVE LOGITS
     quienes
    0.89
     discapacidad
    0.77
     disabilities
    0.77
     якія
    0.75
     who
    0.75
     ktorí
    0.74
    䍜
    0.73
     الذين
    0.73
     whose
    0.73
    ที่มี
    0.72
    Act Density 0.175%

    No Known Activations