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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reviewing and altering systems or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to changes or reforms in systems or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raping
    -0.67
     murders
    -0.64
     murdering
    -0.63
     kills
    -0.62
     sexually
    -0.62
     partying
    -0.61
     KILL
    -0.61
     mates
    -0.61
     killers
    -0.61
     virginity
    -0.61
    POSITIVE LOGITS
    ascript
    0.95
    enary
    0.73
    agraph
    0.68
    ciplinary
    0.68
    actionDate
    0.68
    FAQ
    0.68
    andum
    0.67
    disciplinary
    0.65
    soType
    0.65
    alan
    0.65
    Act Density 0.811%

    No Known Activations