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

    Neuronpedia

    INDEX
    Explanations

    high-ranking officials mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.94
     Horses
    -0.75
    =-=-
    -0.70
    ĸļ
    -0.69
    âĶģ
    -0.69
    âķIJ
    -0.68
    esville
    -0.67
     Bengal
    -0.66
    ||||
    -0.65
    bows
    -0.64
    POSITIVE LOGITS
    dom
    1.03
    ially
    0.86
    doms
    0.76
     overseeing
    0.76
     tasked
    0.74
    IAL
    0.71
    iating
    0.69
    iaries
    0.68
    ulty
    0.68
     sanctioned
    0.67
    Act Density 0.029%

    No Known Activations