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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different levels of government

    oai_token-act-pair · gpt-3.5-turbo

    references to various levels of government or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sund
    -0.82
    ãĥ¡
    -0.75
    vous
    -0.71
    lez
    -0.69
    rogen
    -0.69
     Karin
    -0.66
    yssey
    -0.66
    liction
    -0.65
    ãĥīãĥ©
    -0.65
    oute
    -0.65
    POSITIVE LOGITS
     certific
    0.69
    chart
    0.69
     recognize
    0.66
    abulary
    0.65
     crossings
    0.64
     recognizing
    0.61
    smanship
    0.61
    grounds
    0.61
    chery
    0.61
     rise
    0.60
    Act Density 0.027%

    No Known Activations