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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     invariants
    1.95
     triplets
    1.85
     cohorts
    1.72
     IQR
    1.69
     kelamin
    1.66
     AMT
    1.61
    黢
    1.56
    <0xA6>
    1.55
    苒
    1.55
    কিন্ত
    1.55
    POSITIVE LOGITS
    ﯽ
    2.22
    して
    2.06
    ત
    2.06
    이었
    2.05
    이기
    2.05
    ούς
    2.05
    이면
    2.03
    ير
    2.00
    اب
    1.98
    이니까
    1.96
    Act Density 2.003%

    No Known Activations