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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Was
    0.82
    written
    0.79
     Did
    0.79
    कालिक
    0.78
     after
    0.78
     written
    0.77
    ाये
    0.76
    after
    0.73
    ded
    0.73
    ius
    0.72
    POSITIVE LOGITS
     reiniciar
    1.01
     ο
    0.89
     행복
    0.89
     HNO
    0.89
     나무
    0.88
    ạo
    0.86
     기반
    0.85
    玩具
    0.85
     경로
    0.85
     음악
    0.84
    Act Density 0.000%

    No Known Activations