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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    MAC
    -0.73
    Road
    -0.69
     Bang
    -0.68
    ultan
    -0.67
    rification
    -0.63
    Win
    -0.61
    ixel
    -0.60
     Favor
    -0.60
     Idol
    -0.60
     Candidate
    -0.59
    POSITIVE LOGITS
    ieri
    0.74
    lly
    0.72
    dding
    0.72
    berus
    0.72
     lett
    0.71
     CGI
    0.67
     plumbing
    0.66
    lla
    0.65
     therap
    0.65
    enic
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.