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

    Neuronpedia

    INDEX
    Explanations

    mentions of the acronym "AA" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to academic ratings or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jenner
    -0.77
    ledge
    -0.75
    sticks
    -0.74
    gro
    -0.70
    polit
    -0.69
    lov
    -0.69
    falls
    -0.69
    ende
    -0.67
    nets
    -0.66
    theless
    -0.66
    POSITIVE LOGITS
    BILITIES
    1.00
    BILITY
    0.97
    HHHH
    0.95
    HAHAHAHA
    0.92
    zona
    0.91
    ccess
    0.91
    BIL
    0.90
    VE
    0.89
    ZE
    0.89
    HA
    0.87
    Act Density 0.025%

    No Known Activations