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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different levels of government or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to different levels of governance or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.79
     Sidd
    -0.70
    Sund
    -0.70
    ãĥ¡
    -0.67
     Predators
    -0.65
    Sab
    -0.64
     Pref
    -0.64
    lez
    -0.64
     Karin
    -0.64
    liction
    -0.63
    POSITIVE LOGITS
     certific
    0.77
     crossings
    0.76
    xual
    0.72
    chart
    0.68
    grounds
    0.68
    smanship
    0.65
     embodied
    0.65
     recognize
    0.64
    chery
    0.63
    cule
    0.63
    Act Density 0.025%

    No Known Activations