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

    Neuronpedia

    INDEX
    Explanations

    the concept of fundamental principles or basic knowledge

    oai_token-act-pair · gpt-3.5-turbo

    references to foundational concepts or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.70
    issions
    -0.64
    ated
    -0.64
    oping
    -0.62
    usable
    -0.61
    appa
    -0.60
    imar
    -0.59
    appiness
    -0.59
    Sus
    -0.58
    avement
    -0.57
    POSITIVE LOGITS
    chool
    0.79
    layer
    0.77
    cape
    0.77
     basics
    0.71
    linger
    0.70
    matter
    0.69
    heet
    0.68
    yip
    0.66
     nutshell
    0.66
     fundamentals
    0.64
    Act Density 0.017%

    No Known Activations