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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     victimization
    0.47
     Target
    0.47
     Consid
    0.46
     yourselves
    0.45
     incentivize
    0.45
    cton
    0.44
     familiarize
    0.44
     Ihnen
    0.43
     stellte
    0.43
     Hiring
    0.43
    POSITIVE LOGITS
    ه
    0.57
     Москов
    0.55
    econ
    0.50
    shen
    0.50
    mén
    0.49
    ن
    0.49
     però
    0.48
    โล
    0.48
    ین
    0.47
    ولندا
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.