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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    id
    0.80
    ست
    0.79
    0.73
    ล
    0.71
    à
    0.68
    hierarchy
    0.68
    اس
    0.67
    ض
    0.67
    hnt
    0.67
    hj
    0.66
    POSITIVE LOGITS
     salient
    0.78
    ма
    0.75
     consecrated
    0.75
     faptul
    0.73
     bahsed
    0.72
     prophet
    0.70
     commander
    0.68
     rugs
    0.68
     pepperoni
    0.67
    说说
    0.67
    Act Density 0.172%

    No Known Activations