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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ana" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.93
    neys
    -0.90
    nesday
    -0.85
    kefeller
    -0.83
    yright
    -0.81
    GoldMagikarp
    -0.81
    auld
    -0.78
    tyard
    -0.77
    drm
    -0.69
    akedown
    -0.69
    POSITIVE LOGITS
    uthor
    1.01
    issance
    0.97
    utical
    0.90
    qua
    0.89
    heim
    0.89
    eus
    0.89
    esthesia
    0.88
    emia
    0.86
     Grande
    0.82
    ea
    0.78
    Act Density 0.019%

    No Known Activations