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

    Neuronpedia

    INDEX
    Explanations

    phrases related to laws, regulations, and enforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to imposing rules or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sembly
    -0.66
    adelphia
    -0.65
    uble
    -0.64
    pring
    -0.64
    addin
    -0.62
    ournals
    -0.61
    uana
    -0.60
    connected
    -0.59
     Room
    -0.57
    ource
    -0.57
    POSITIVE LOGITS
     restrictions
    1.04
     curfew
    0.97
     punishments
    0.96
     onto
    0.94
     brakes
    0.93
     burdens
    0.93
     draconian
    0.91
     harsher
    0.89
     quotas
    0.88
     penalties
    0.88
    Act Density 0.190%

    No Known Activations