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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     confir
    -0.90
    ij士
    -0.79
    cair
    -0.78
     htt
    -0.77
     sovere
    -0.77
    sbm
    -0.74
    à¼
    -0.73
    bourg
    -0.72
    ilater
    -0.71
     Gujar
    -0.71
    POSITIVE LOGITS
    metal
    0.70
    Merit
    0.66
    ciples
    0.64
    istics
    0.63
    âĺħâĺħ
    0.62
    outine
    0.62
    aper
    0.61
    plates
    0.61
     downed
    0.60
     metric
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.