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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     j
    0.44
     J
    0.40
    sham
    0.39
     ஜ
    0.39
     taka
    0.38
     bj
    0.38
    hasa
    0.38
    마다
    0.37
     als
    0.37
    ័យ
    0.37
    POSITIVE LOGITS
    REN
    0.40
    Ced
    0.38
     REN
    0.38
    CED
    0.38
     Lieber
    0.38
    Loire
    0.37
    𝑀
    0.37
    toc
    0.37
    CopyWith
    0.37
    فی
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.