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

    Neuronpedia

    INDEX
    Explanations

    references to academia and academics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of academia and academic professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Islanders
    -0.76
     Islands
    -0.73
     Territories
    -0.71
     Island
    -0.65
     Sailor
    -0.64
    orders
    -0.62
     takeoff
    -0.62
     Niagara
    -0.60
     shore
    -0.59
     flight
    -0.59
    POSITIVE LOGITS
    chool
    1.05
    essors
    1.01
    hran
    1.00
    DragonMagazine
    0.93
     academia
    0.91
     academics
    0.91
    krit
    0.90
    essor
    0.89
     lecturer
    0.89
    ynthesis
    0.89
    Act Density 0.023%

    No Known Activations