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

    Neuronpedia

    INDEX
    Explanations

    phrases related to eligibility criteria for advertisements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to eligibility and restrictions for advertising

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffe
    -0.76
     Maze
    -0.73
    atl
    -0.70
    miah
    -0.69
    erity
    -0.68
     Talks
    -0.64
    roads
    -0.62
    rote
    -0.62
    forts
    -0.62
    mosp
    -0.62
    POSITIVE LOGITS
     disqual
    1.22
     qualifies
    1.16
     qualify
    1.08
     exempt
    0.99
     eligible
    0.98
     ineligible
    0.97
     disqualified
    0.93
     acceptable
    0.93
     deserving
    0.93
     worthy
    0.89
    Act Density 1.131%

    No Known Activations