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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity and diversity across different demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IBOutlet
    -0.61
    )))),
    -0.52
    )()
    -0.51
    setViewName
    -0.50
    "}";
    -0.50
    Související
    -0.50
    audiovisuel
    -0.50
    Only
    -0.49
    xsi
    -0.49
    only
    -0.49
    POSITIVE LOGITS
     regardless
    0.91
    regardless
    0.85
     irrespective
    0.77
     apapun
    0.77
    不论
    0.76
     everywhere
    0.72
     любого
    0.71
     Regardless
    0.70
    无论
    0.70
    不管是
    0.69
    Act Density 0.232%

    No Known Activations