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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     apple
    0.54
     into
    0.53
     push
    0.52
    apple
    0.51
     in
    0.50
     strikes
    0.50
     scratched
    0.49
     brewed
    0.49
     pocket
    0.49
     small
    0.49
    POSITIVE LOGITS
    êmio
    0.54
     తన
    0.53
    絬
    0.48
     призна
    0.47
     مقار
    0.47
     Latinoamérica
    0.46
    囫
    0.46
     защото
    0.46
     డే
    0.46
     сет
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.