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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific public figures and their actions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resso
    -0.65
     Archdemon
    -0.65
     Directions
    -0.64
    isu
    -0.64
     repositories
    -0.64
     Puzzle
    -0.64
    apo
    -0.62
    IRE
    -0.61
    sett
    -0.60
     rall
    -0.59
    POSITIVE LOGITS
    gyn
    1.47
    ancel
    1.01
    uala
    0.87
     Huckabee
    0.86
    atur
    0.81
     Kelly
    0.79
    oad
    0.77
    ously
    0.77
    iliate
    0.74
     Emin
    0.74
    Act Density 0.005%

    No Known Activations