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

    Neuronpedia

    INDEX
    Explanations

    the term "non" in various contexts indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.99
     proprement
    -0.88
     Мексичка
    -0.81
    LabelTagHelper
    -0.81
    ValueStyle
    -0.80
    发表于
    -0.78
     Vikipedi
    -0.77
     Theſe
    -0.77
     rumahnya
    -0.76
    myModal
    -0.75
    POSITIVE LOGITS
     non
    2.56
    Non
    2.50
     Non
    2.48
    non
    2.34
     NON
    2.30
    NON
    2.08
    非
    1.92
     Nons
    1.54
     非
    1.54
     nons
    1.53
    Act Density 0.084%

    No Known Activations