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

    Neuronpedia

    INDEX
    Explanations

    mentions of "AA" (American Association) followed by a mix of different words

    oai_token-act-pair · gpt-3.5-turbo

    references to the American Association of University Professors (AAUP) and associated ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jenner
    -0.87
     Canaver
    -0.72
    ledge
    -0.71
    lov
    -0.69
    theless
    -0.68
    ician
    -0.67
    polit
    -0.67
    pheus
    -0.66
    sticks
    -0.65
    ophers
    -0.65
    POSITIVE LOGITS
    BILITIES
    0.93
    BILITY
    0.92
    zona
    0.87
    BIL
    0.86
    HHHH
    0.85
    BA
    0.83
    HR
    0.83
    VE
    0.82
    illac
    0.82
    HAHAHAHA
    0.82
    Act Density 0.013%

    No Known Activations