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

    Neuronpedia

    INDEX
    Explanations

    common names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     td
    -0.76
    ¥µ
    -0.74
    bidden
    -0.74
    iminary
    -0.67
    iculty
    -0.66
    fecture
    -0.66
    mble
    -0.65
    hops
    -0.62
    pmwiki
    -0.61
    sites
    -0.60
    POSITIVE LOGITS
     Hardy
    0.81
     Wasserman
    0.81
     Cohen
    0.78
     Klein
    0.78
     Reed
    0.77
     Zimmer
    0.77
     Snyder
    0.77
     Wolfe
    0.76
     Kennedy
    0.76
     Buckley
    0.76
    Act Density 0.252%

    No Known Activations