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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    doesn
    1.16
     isn
    1.15
    don
    1.14
    MeToo
    1.14
    €™
    1.13
     ਹੈ
    1.13
     neće
    1.12
     doesn
    1.11
     будет
    1.11
     خواهد
    1.09
    POSITIVE LOGITS
    ;
    1.04
     SPMs
    1.01
     and
    0.97
     dignitaries
    0.96
     the
    0.94
    စိတ်အပိုင်း
    0.92
    并通过
    0.91
    <unused330>
    0.91
    :
    0.90
    𝑣
    0.90
    Act Density 4.068%

    No Known Activations