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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    itives
    -0.71
    stice
    -0.69
    cgi
    -0.69
    hest
    -0.67
    breaks
    -0.66
    fect
    -0.66
    estones
    -0.65
    ggies
    -0.65
    reads
    -0.65
    arella
    -0.65
    POSITIVE LOGITS
     appell
    0.82
    soDeliveryDate
    0.70
     mathemat
    0.68
     inund
    0.63
     constitu
    0.62
    utterstock
    0.62
     husbands
    0.62
    ãĥĩ
    0.61
     subsidies
    0.61
     VID
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.