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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Also
    0.63
     Yeşil
    0.63
     obeys
    0.61
    olojik
    0.58
    Also
    0.57
     znak
    0.55
     aktuellen
    0.55
     remains
    0.55
    らん
    0.54
     Bigger
    0.54
    POSITIVE LOGITS
    這些
    0.73
    这些
    0.72
     these
    0.68
    これらの
    0.67
     desses
    0.66
    these
    0.63
     இவை
    0.63
    เหล่านี้
    0.62
    These
    0.60
    ––
    0.59
    Act Density 0.376%

    No Known Activations