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

    Neuronpedia

    INDEX
    Explanations

    high-ranking official positions in government or military

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles related to government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.88
    crew
    -0.85
    nikov
    -0.84
    kinson
    -0.74
    ensis
    -0.71
    MpServer
    -0.71
    eros
    -0.69
    eat
    -0.69
    crow
    -0.69
    elled
    -0.68
    POSITIVE LOGITS
     Tim
    0.98
     Stephen
    0.95
     Bill
    0.93
     Mark
    0.93
     Steve
    0.92
     Ann
    0.92
     David
    0.92
     George
    0.92
     Patrick
    0.91
     Shaun
    0.91
    Act Density 0.129%

    No Known Activations