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

    Neuronpedia

    INDEX
    Explanations

    affirmations of capability or endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TestBed
    -0.57
    彼らは
    -0.46
     العد
    -0.45
    Externí
    -0.44
    ריים
    -0.43
     impeach
    -0.42
    RAIN
    -0.42
    Hozzáférés
    -0.42
     ioutil
    -0.42
    JU
    -0.41
    POSITIVE LOGITS
    protoimpl
    0.87
     Baillargeon
    0.73
    parsedMessage
    0.69
    WebServlet
    0.68
     otomatig
    0.67
    Geplaatst
    0.67
    Сюжет
    0.66
     محفوظة
    0.65
     تضيفلها
    0.65
    AutoresizingMask
    0.65
    Act Density 0.125%

    No Known Activations