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

    Neuronpedia

    INDEX
    Explanations

    references to civil liberties organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to civil liberties organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    smart
    -0.81
     srfAttach
    -0.62
    xit
    -0.61
    thin
    -0.61
    balls
    -0.60
     traumatic
    -0.60
    ripp
    -0.59
    iph
    -0.59
    tra
    -0.59
     deduct
    -0.59
    POSITIVE LOGITS
     Liberties
    1.88
     liberties
    0.94
    terness
    0.90
    IGHTS
    0.90
     ACLU
    0.89
     freedoms
    0.83
    uthor
    0.80
    ights
    0.79
     Rights
    0.79
    umbered
    0.77
    Act Density 0.003%

    No Known Activations