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

    Neuronpedia

    INDEX
    Explanations

    mentions of different levels of government

    oai_token-act-pair · gpt-3.5-turbo

    references to various hierarchical levels within organizations or society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sund
    -0.73
    ãĥ¡
    -0.73
    ãĥĺ
    -0.72
    liction
    -0.71
    lez
    -0.69
    ãĥīãĥ©
    -0.68
    lict
    -0.66
    ãģ¦
    -0.66
    ãĥĨ
    -0.66
    ãĥĩ
    -0.65
    POSITIVE LOGITS
     certific
    0.71
     enrichment
    0.69
     crossings
    0.67
    atics
    0.67
     recognition
    0.66
    hips
    0.65
     rise
    0.65
     recognize
    0.62
     recognizing
    0.62
     onwards
    0.62
    Act Density 0.030%

    No Known Activations