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

    Neuronpedia

    INDEX
    Explanations

    mentions of academics

    oai_token-act-pair · gpt-3.5-turbo

    references to academia and academic professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Islands
    -0.71
     Territories
    -0.68
     windows
    -0.67
     Niagara
    -0.67
     birth
    -0.65
     Canal
    -0.65
     window
    -0.61
    val
    -0.60
     Orleans
    -0.59
    Gun
    -0.59
    POSITIVE LOGITS
     academics
    1.17
    orem
    0.94
    chool
    0.91
    ertation
    0.90
     academia
    0.90
     lecturer
    0.88
     challeng
    0.88
    hran
    0.87
    ervatives
    0.86
     academ
    0.86
    Act Density 0.020%

    No Known Activations