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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sources, such as "source of income" or "source of power"

    oai_token-act-pair · gpt-3.5-turbo

    references to sources or origins of various concepts, entities, or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oser
    -0.70
     Taken
    -0.69
    heses
    -0.69
     Lenn
    -0.67
    ectomy
    -0.66
    bags
    -0.64
    sequ
    -0.64
    suits
    -0.64
    quet
    -0.64
    ramids
    -0.63
    POSITIVE LOGITS
     inspiration
    1.49
     income
    1.25
     revenue
    1.19
     livelihood
    1.19
     sust
    1.16
     funding
    1.05
     illumination
    1.04
     contention
    0.98
     motivation
    0.97
     distraction
    0.93
    Act Density 0.133%

    No Known Activations