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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     be
    0.64
     in
    0.56
     the
    0.54
     an
    0.48
     في
    0.47
     that
    0.45
     f
    0.44
    that
    0.43
     this
    0.43
     fungal
    0.43
    POSITIVE LOGITS
    월
    0.55
    ヶ月
    0.52
    ０
    0.52
    4
    0.50
    丁目
    0.50
    0
    0.49
    하지
    0.49
    时代
    0.49
     derivada
    0.49
    ️⃣
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.