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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.57
     الحره
    -0.56
     trône
    -0.56
     BorderRadius
    -0.55
    Obrázky
    -0.54
     futuras
    -0.53
     colgantes
    -0.53
    :✨
    -0.52
     '\\;'
    -0.51
    érrez
    -0.50
    POSITIVE LOGITS
    ]<<"
    0.67
     "")
    0.64
    CodeAttribute
    0.64
    則
    0.63
    </caption>
    0.62
    TestBed
    0.61
    Begriffsklä
    0.55
    roth
    0.54
     Saltar
    0.54
    GraphicsUnit
    0.54
    Act Density 0.242%

    No Known Activations