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

    Neuronpedia

    INDEX
    Explanations

    themes related to decision-making and personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pursuing goals and self-improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ApiException
    -0.57
    fjspx
    -0.57
     betweenstory
    -0.54
    usercontent
    -0.52
    LError
    -0.51
    Ƚ
    -0.51
     CanadaChoose
    -0.49
    aarrggbb
    -0.49
    RegressionTest
    -0.49
     Мексичка
    -0.48
    POSITIVE LOGITS
     your
    0.35
    onha
    0.31
     fertile
    0.30
     ENTRE
    0.29
     travailleurs
    0.28
     Archi
    0.28
     "$@"
    0.28
    ItemIndex
    0.28
     ché
    0.28
     Nietzsche
    0.28
    Act Density 0.045%

    No Known Activations