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

    Neuronpedia

    INDEX
    Explanations

    references to male and female characters in contexts of action or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aikana
    -0.55
     vermag
    -0.54
    ++]=
    -0.52
     lisäksi
    -0.50
     XXI
    -0.48
    __)
    -0.48
    ின்ற
    -0.48
     Aurelius
    -0.47
    раздо
    -0.46
    我也是
    -0.46
    POSITIVE LOGITS
    เค้า
    0.79
     BoxDecoration
    0.73
    WarningLevel
    0.72
     سكانية
    0.72
    IntentFilter
    0.71
     kasarigan
    0.67
     مواليد
    0.66
    WebServlet
    0.65
    StructEnd
    0.63
    хьтан
    0.60
    Act Density 0.259%

    No Known Activations