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

    Neuronpedia

    INDEX
    Explanations

    discussions about motivation and incentives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xiety
    -0.15
    /email
    -0.15
    ertime
    -0.15
    auer
    -0.14
    itte
    -0.14
    ery
    -0.14
    weeney
    -0.14
    æ¡Ī
    -0.14
    alice
    -0.13
    imony
    -0.13
    POSITIVE LOGITS
    595
    0.16
    FileManager
    0.15
    帯
    0.15
    amedi
    0.15
    CTS
    0.14
    bras
    0.14
    iras
    0.14
    Bindable
    0.14
    .undo
    0.14
    488
    0.14
    Act Density 0.038%

    No Known Activations