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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     $=$
    1.55
    ='
    1.45
     dictionary
    1.42
     href
    1.34
    孭
    1.33
     international
    1.31
     ann
    1.31
    ＠
    1.31
    ﹗
    1.31
     Organisation
    1.31
    POSITIVE LOGITS
    they
    2.66
    彼は
    2.62
     він
    2.44
     он
    2.39
    They
    2.35
     они
    2.31
     họ
    2.26
    she
    2.26
     he
    2.23
     they
    2.21
    Act Density 0.470%

    No Known Activations