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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     inst
    0.92
    ним
    0.90
    옹
    0.85
    路上
    0.84
    不要
    0.82
     terminal
    0.82
     tarn
    0.81
    थियों
    0.80
    acu
    0.80
    Bride
    0.79
    POSITIVE LOGITS
    myn
    0.99
     maximising
    0.97
    Ky
    0.93
    )})
    0.92
    mnopqrst
    0.91
    <unused231>
    0.91
     MNRAS
    0.90
    s
    0.89
     maximizing
    0.89
    ))*(
    0.87
    Act Density 0.000%

    No Known Activations