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

    Neuronpedia

    INDEX
    Explanations

    references to airplanes

    oai_token-act-pair · gpt-3.5-turbo

    references to airplanes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongyang
    -0.79
    urai
    -0.77
    pheus
    -0.77
    hon
    -0.76
    isters
    -0.74
    neutral
    -0.74
    rete
    -0.73
    nan
    -0.73
    til
    -0.73
    olith
    -0.72
    POSITIVE LOGITS
     Airlines
    0.73
     Turbo
    0.69
    urdue
    0.68
     Marriott
    0.64
    UX
    0.63
    cart
    0.63
    vier
    0.62
    aughed
    0.62
     Simulator
    0.61
    ously
    0.61
    Act Density 0.026%

    No Known Activations