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

    Neuronpedia

    INDEX
    Explanations

    references to creativity and the mind's ability to conjure ideas and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to imagination and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atern
    -0.69
    metal
    -0.68
    names
    -0.67
    ten
    -0.67
    ne
    -0.67
    carbon
    -0.67
    von
    -0.66
    hide
    -0.65
    fixed
    -0.64
    ãĥİ
    -0.64
    POSITIVE LOGITS
    smanship
    0.95
     imagination
    0.87
    ibility
    0.85
     creativity
    0.85
     juices
    0.83
     creatively
    0.79
    issance
    0.79
    urable
    0.69
     curiosity
    0.68
     inspiring
    0.67
    Act Density 0.031%

    No Known Activations