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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ageddon
    -0.68
    olitical
    -0.64
    olia
    -0.63
     Oath
    -0.62
    rendered
    -0.62
     polic
    -0.60
     insured
    -0.60
    athered
    -0.58
    ufact
    -0.58
     bailed
    -0.58
    POSITIVE LOGITS
    Interstitial
    0.79
    hov
    0.69
     Flavoring
    0.67
     compulsion
    0.66
    ippers
    0.65
    Plugin
    0.64
    ãĥĥãĤ¯
    0.63
    rawdownloadcloneembedreportprint
    0.63
    ikers
    0.63
    cv
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.