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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     any
    0.61
     creates
    0.60
    除非
    0.60
     большинства
    0.56
    }
    0.56
         
    0.54
     *
    0.54
     mischievous
    0.54
     create
    0.54
     oluş
    0.54
    POSITIVE LOGITS
     tại
    0.97
     ở
    0.93
    ជាមួយ
    0.88
     στη
    0.82
     aboard
    0.78
     zajedno
    0.76
     presso
    0.75
    ກັບ
    0.75
    年在
    0.75
     Tại
    0.75
    Act Density 0.001%

    No Known Activations