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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vernment
    -0.78
    illary
    -0.71
    llan
    -0.66
     intern
    -0.63
    bernatorial
    -0.63
    illon
    -0.62
    zzi
    -0.60
    illery
    -0.60
    itte
    -0.59
    anian
    -0.58
    POSITIVE LOGITS
     è£ıè
    0.69
     Franch
    0.67
    rawdownloadcloneembedreportprint
    0.66
     SERV
    0.63
    KA
    0.63
    ews
    0.62
    SIZE
    0.62
    ashtra
    0.61
    pod
    0.61
    MU
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.