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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     quarta
    0.53
     cuarta
    0.51
     ଚ
    0.51
    bottle
    0.50
    ări
    0.49
     bottle
    0.49
     został
    0.48
     බල
    0.48
    than
    0.47
    ıp
    0.47
    POSITIVE LOGITS
     Passo
    0.45
    🙏🏻
    0.41
    一同
    0.40
    ↵
    0.40
    陘
    0.40
     психологи
    0.39
    这个时候
    0.39
     lewis
    0.39
    צב
    0.39
     обстоятельства
    0.39
    Act Density 0.000%

    No Known Activations