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

    Neuronpedia

    INDEX
    Explanations

    the word "Cu" at varying levels of similarity

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Cupertino

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aid
    -0.75
    hips
    -0.75
     Nanto
    -0.68
     Pathfinder
    -0.67
     Fundamental
    -0.64
     Cosponsors
    -0.64
    manship
    -0.63
     Asylum
    -0.62
     PID
    -0.61
    making
    -0.61
    POSITIVE LOGITS
    isine
    1.56
    untu
    1.03
    adr
    0.97
    illin
    0.96
    adra
    0.95
    vette
    0.92
    asts
    0.91
    PLIC
    0.91
    vier
    0.91
    eto
    0.91
    Act Density 0.013%

    No Known Activations