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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical locations and actions taking place

    oai_token-act-pair · gpt-3.5-turbo

    scenes involving social interactions in a community setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Conclusion
    -0.84
    Additionally
    -0.76
    Therefore
    -0.73
    Currently
    -0.72
    Firstly
    -0.72
    Background
    -0.71
     [+
    -0.71
    )",
    -0.70
    )).
    -0.70
     Lets
    -0.69
    POSITIVE LOGITS
     indign
    0.79
     thrill
    0.75
     postwar
    0.75
     poets
    0.73
     solitude
    0.73
     exhilar
    0.73
     scrib
    0.73
     murm
    0.73
     melancholy
    0.72
     gle
    0.72
    Act Density 1.874%

    No Known Activations