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

    Neuronpedia

    INDEX
    Explanations

    phrases related to compliance and adherence to rules or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to adherence to laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulz
    -0.74
    alone
    -0.73
    OY
    -0.70
    ILL
    -0.68
    disk
    -0.68
    hor
    -0.68
    allo
    -0.68
    OTA
    -0.67
    andals
    -0.66
     Rubber
    -0.64
    POSITIVE LOGITS
    uary
    0.91
    formance
    0.81
    chwitz
    0.78
    lihood
    0.78
     accordance
    0.76
     Dragonbound
    0.75
     arrangement
    0.73
    ively
    0.72
    eous
    0.71
    lia
    0.70
    Act Density 0.011%

    No Known Activations