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

    Neuronpedia

    INDEX
    Explanations

    terms related to legislative or regulatory actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal classifications and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intrig
    -0.76
    soType
    -0.71
     mir
    -0.70
    wow
    -0.69
    mess
    -0.69
     killer
    -0.65
    Wow
    -0.64
     attm
    -0.63
     Niet
    -0.63
     miracle
    -0.62
    POSITIVE LOGITS
     ineligible
    1.18
     exempted
    1.06
     exempt
    1.04
     automatically
    1.02
     eligible
    0.99
     concess
    0.96
     prohibited
    0.95
     forfeit
    0.95
     barred
    0.94
     disqualified
    0.91
    Act Density 0.425%

    No Known Activations