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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority and enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of imposing various rules, regulations, or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pring
    -0.73
    adelphia
    -0.68
    auga
    -0.62
    imeo
    -0.62
    ahoo
    -0.61
    uncture
    -0.59
    ffer
    -0.58
    addin
    -0.58
    uana
    -0.58
     interviewer
    -0.57
    POSITIVE LOGITS
     stricter
    0.90
     reforms
    0.89
     policies
    0.88
     principles
    0.86
     restrictions
    0.85
     stringent
    0.83
     strict
    0.82
     corrective
    0.81
     directives
    0.80
    itarian
    0.80
    Act Density 0.355%

    No Known Activations