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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policies and actions aimed at regulating or controlling access to various items or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with access and regulation of societal resources and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.80
    ©¶æ¥µ
    -0.77
    DragonMagazine
    -0.73
     Canaver
    -0.70
     Cosponsors
    -0.68
    stanbul
    -0.67
    ħĭ
    -0.65
    ellen
    -0.64
     Treasurer
    -0.64
     Manafort
    -0.61
    POSITIVE LOGITS
     injust
    0.98
     these
    0.97
     harm
    0.96
     harmful
    0.96
     injustice
    0.93
     harms
    0.93
     crappy
    0.90
     evils
    0.89
     ourselves
    0.89
     lifes
    0.88
    Act Density 0.607%

    No Known Activations