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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     arrang
    -0.82
     Compar
    -0.74
    onse
    -0.73
     postage
    -0.72
     subsequ
    -0.68
     ado
    -0.65
    stration
    -0.65
    iton
    -0.64
    xus
    -0.63
     compr
    -0.63
    POSITIVE LOGITS
    lay
    0.86
    mia
    0.73
    acre
    0.72
     Gund
    0.67
    embed
    0.67
    ickr
    0.64
    aez
    0.62
    ixel
    0.62
    '),
    0.62
    olen
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.