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

    Neuronpedia

    INDEX
    Explanations

    mentions of law enforcement and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auga
    -0.91
    iliary
    -0.87
    ngth
    -0.78
    yip
    -0.77
    voy
    -0.71
    hetically
    -0.70
    hiba
    -0.69
    rik
    -0.69
    cair
    -0.69
    riks
    -0.68
    POSITIVE LOGITS
    enforcement
    0.91
    abiding
    0.78
     jurisdiction
    0.76
     precedent
    0.74
    riage
    0.74
     ACTIONS
    0.71
    ASED
    0.70
     Queensland
    0.68
     looph
    0.68
     apartheid
    0.67
    Act Density 0.233%

    No Known Activations