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

    Neuronpedia

    INDEX
    Explanations

    phrases related to laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arat
    -0.71
    been
    -0.66
    ucci
    -0.66
     condem
    -0.64
    wcs
    -0.62
    likely
    -0.59
     listing
    -0.58
    endif
    -0.58
     privile
    -0.58
    BuyableInstoreAndOnline
    -0.57
    POSITIVE LOGITS
     certain
    0.77
     these
    0.68
     oneself
    0.67
     goods
    0.67
     course
    0.66
     Goods
    0.63
    irgin
    0.63
     abroad
    0.62
     any
    0.62
     those
    0.61
    Act Density 0.152%

    No Known Activations