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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to ownership

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imar
    -0.70
     slew
    -0.61
     sclerosis
    -0.60
     maturity
    -0.59
    annel
    -0.57
    ropolis
    -0.56
     scaling
    -0.56
    olson
    -0.55
     inacc
    -0.55
    ugu
    -0.54
    POSITIVE LOGITS
    ences
    0.87
     exclusively
    0.87
     to
    0.83
     toget
    0.79
     solely
    0.79
     squarely
    0.79
    BuyableInstoreAndOnline
    0.78
    ĪĴ
    0.72
     nowhere
    0.72
     belong
    0.71
    Act Density 0.039%

    No Known Activations