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

    Neuronpedia

    INDEX
    Explanations

    references to the word "our."

    oai_token-act-pair · gpt-3.5-turbo

    references to collective ownership or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.73
     steroids
    -0.71
    arlane
    -0.69
    ulators
    -0.65
     Rasmussen
    -0.62
     relapse
    -0.62
    ota
    -0.59
     payday
    -0.58
    ORN
    -0.58
    ulator
    -0.58
    POSITIVE LOGITS
    neau
    1.24
    selves
    1.19
    neys
    1.18
    dain
    1.17
    cery
    1.07
    tesy
    1.01
    ishment
    0.95
    ¯¯¯¯¯¯¯¯
    0.94
    dan
    0.93
    izons
    0.93
    Act Density 0.038%

    No Known Activations