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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     finished
    0.81
    burnt
    0.76
     allotted
    0.76
    finished
    0.76
    nitz
    0.75
    ⓢ
    0.75
    Decrypt
    0.74
     allocated
    0.74
    /*
    0.72
     transposed
    0.72
    POSITIVE LOGITS
    רק
    0.84
    શન
    0.81
    шення
    0.76
    শন
    0.76
    ledning
    0.73
    শনের
    0.73
    মিন
    0.72
    lug
    0.72
     كن
    0.71
    শনে
    0.71
    Act Density 0.000%

    No Known Activations