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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     valuables
    0.79
     forwarded
    0.77
     friendly
    0.76
     wiped
    0.73
     undermined
    0.73
     Osborne
    0.72
     вой
    0.71
     favorables
    0.71
    可能です
    0.71
     burrow
    0.71
    POSITIVE LOGITS
    ר
    0.82
    ligare
    0.73
    ץ
    0.73
    ्स
    0.73
    ριθ
    0.71
    ס
    0.68
    Defendants
    0.67
    overlaps
    0.67
    ג
    0.67
    eslint
    0.66
    Act Density 0.001%

    No Known Activations