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 "sources of inspiration."

    oai_token-act-pair · gpt-3.5-turbo

    references to sources of influence or power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.76
    ectomy
    -0.74
     Machines
    -0.72
    heses
    -0.72
    boxing
    -0.71
    odore
    -0.71
    oser
    -0.71
    gdala
    -0.69
    Downloadha
    -0.69
    suits
    -0.69
    POSITIVE LOGITS
     inspiration
    1.57
     income
    1.25
     sust
    1.23
     revenue
    1.22
     livelihood
    1.13
     information
    1.06
     funding
    1.06
     funds
    1.02
     illumination
    1.00
     motivation
    0.99
    Act Density 0.118%

    No Known Activations