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

    Neuronpedia

    INDEX
    Explanations

    references to personal commitments and absences due to health or scheduling issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asuring
    -0.75
     rapists
    -0.72
     Zup
    -0.70
     plurality
    -0.69
    galitarian
    -0.69
    ACP
    -0.68
     perpetrators
    -0.65
    NRS
    -0.64
     replicated
    -0.64
    olen
    -0.62
    POSITIVE LOGITS
     hiatus
    1.19
     commitments
    1.01
     touring
    0.98
     retirement
    0.96
     illness
    0.95
     vacation
    0.94
     distractions
    0.92
     engagements
    0.89
     renovations
    0.88
     vacations
    0.87
    Act Density 0.580%

    No Known Activations