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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pulled
    0.65
     pull
    0.64
     l
    0.64
     rappers
    0.62
     poets
    0.61
     Crew
    0.60
     protagonistas
    0.60
     descend
    0.58
     d
    0.58
     volle
    0.57
    POSITIVE LOGITS
    关于
    0.80
    bursement
    0.73
    什么是
    0.70
    是一种
    0.68
    חה
    0.68
    loans
    0.68
    isations
    0.67
     ஆலோசனை
    0.66
    investment
    0.66
    。
    0.65
    Act Density 0.009%

    No Known Activations