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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ethics
    0.45
     Amsterdam
    0.45
    CS
    0.44
    Amsterdam
    0.44
     at
    0.44
    PL
    0.43
    Markets
    0.43
    Residence
    0.43
    Berlin
    0.42
    CM
    0.42
    POSITIVE LOGITS
    amom
    0.47
    ῦ
    0.47
    يدة
    0.47
    愊
    0.46
    egang
    0.46
     deseas
    0.45
    வனுக்கு
    0.44
    erde
    0.44
     hele
    0.43
    后面
    0.43
    Act Density 0.000%

    No Known Activations