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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     zowel
    0.93
     더욱
    0.90
     upravo
    0.89
     sowohl
    0.88
     spécialement
    0.88
     さらに
    0.85
    不仅
    0.85
     również
    0.84
     zudem
    0.84
     وحتى
    0.82
    POSITIVE LOGITS
     superficially
    2.07
     nominally
    1.59
     ostensibly
    1.59
     technically
    1.56
     certes
    1.56
     theoretically
    1.44
     admittedly
    1.40
     SOME
    1.35
    確かに
    1.31
     certainly
    1.30
    Act Density 2.491%

    No Known Activations