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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     실행
    0.83
    arantad
    0.83
    Ia
    0.81
    ੳ
    0.79
     조
    0.76
     nomin
    0.74
     pyt
    0.73
     Shel
    0.71
    í
    0.71
     주
    0.70
    POSITIVE LOGITS
     attire
    1.13
     achromatic
    0.97
     lanyard
    0.93
     仕事
    0.86
     posture
    0.84
     office
    0.81
    scientific
    0.80
     irritate
    0.80
     forehead
    0.80
     trousers
    0.79
    Act Density 0.938%

    No Known Activations