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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    我要
    0.52
     хотите
    0.51
     chcesz
    0.49
    Callable
    0.48
     $*
    0.47
    wach
    0.46
    ệnh
    0.46
     説明
    0.45
     должны
    0.45
     নিচে
    0.45
    POSITIVE LOGITS
     similarly
    0.96
     similaires
    0.89
     similaire
    0.85
     Similarly
    0.84
     similar
    0.81
     counterpart
    0.81
    类似的
    0.80
    Similarly
    0.79
    similar
    0.76
     Likewise
    0.75
    Act Density 0.045%

    No Known Activations