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

    Neuronpedia

    INDEX
    Explanations

    word combinations related to illegal or prohibited actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal offenses and crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lets
    -0.80
    quickShipAvailable
    -0.72
    reens
    -0.71
    wark
    -0.70
    opian
    -0.69
    amera
    -0.69
    NetMessage
    -0.69
    lett
    -0.68
     livest
    -0.68
    ulously
    -0.67
    POSITIVE LOGITS
     punishable
    1.19
     offences
    1.02
     offence
    0.92
     offenses
    0.90
     incurred
    0.85
     involving
    0.85
     committed
    0.83
     levied
    0.80
     conviction
    0.80
     arising
    0.78
    Act Density 0.040%

    No Known Activations