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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    etc
    0.57
    Which
    0.57
    P
    0.54
    Although
    0.53
    I
    0.51
    Including
    0.50
    Is
    0.50
    M
    0.49
    Since
    0.49
     ইত্যাদি
    0.48
    POSITIVE LOGITS
     twofold
    1.16
     threefold
    1.08
     undoubtedly
    1.03
     akin
    1.03
     supposed
    1.02
     tantamount
    0.96
     probably
    0.93
     simply
    0.93
     meant
    0.92
     arguably
    0.89
    Act Density 1.190%

    No Known Activations