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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    م
    1.62
    в
    1.54
    <unused44>
    1.53
    ho
    1.49
     piensan
    1.48
    ը
    1.46
     bakt
    1.43
     cie
    1.42
    ve
    1.42
    به
    1.42
    POSITIVE LOGITS
    ≙
    1.69
     whose
    1.65
    luğu
    1.61
     caffeine
    1.55
     whereabouts
    1.54
    1.52
    1.52
     preventing
    1.52
    oned
    1.50
     poté
    1.48
    Act Density 0.000%

    No Known Activations