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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "ordinary" or "normal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.54
    getOutputStream
    -0.45
    MLLoader
    -0.45
    ServletConfig
    -0.42
    AnchorTagHelper
    -0.39
     gynhyrchwyd
    -0.38
     divorce
    -0.37
     مشارکت‌کنندگان
    -0.36
     Divorce
    -0.36
     blame
    -0.36
    POSITIVE LOGITS
     unusual
    1.73
     abnormal
    1.55
    Unusual
    1.55
    unusual
    1.55
     Unusual
    1.55
    normal
    1.42
    ordinary
    1.42
     normal
    1.42
     ordinary
    1.39
     extraordinary
    1.36
    Act Density 0.222%

    No Known Activations