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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    emi
    -0.76
    efe
    -0.76
    hens
    -0.76
    dL
    -0.74
    aco
    -0.72
    xus
    -0.70
    GGGGGGGG
    -0.70
    eed
    -0.69
    ajor
    -0.68
    PP
    -0.68
    POSITIVE LOGITS
     attached
    0.76
     Develop
    0.67
    actionDate
    0.67
     Wikimedia
    0.66
     Wal
    0.63
    HEAD
    0.63
     Kaplan
    0.60
     Craigslist
    0.60
     Lancaster
    0.59
     Mechan
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.