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

    Neuronpedia

    INDEX
    Explanations

    phrases related to anti-something, potentially indicating a focus on items or concepts associated with being against or counteracting something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anti-technology and anti-regulatory themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Halls
    -0.76
    shire
    -0.72
     Chaff
    -0.71
     Pelicans
    -0.69
    INGS
    -0.67
    ourcing
    -0.67
     Remastered
    -0.66
     Cosponsors
    -0.66
     Kinn
    -0.65
    theless
    -0.64
    POSITIVE LOGITS
    zac
    0.89
    war
    0.87
    hero
    0.85
    establishment
    0.84
    drug
    0.84
    strate
    0.83
    digy
    0.81
    hesis
    0.81
    abortion
    0.81
    anti
    0.80
    Act Density 0.017%

    No Known Activations