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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FlatAppearance
    -0.44
    ViewFeatures
    -0.40
    WebControls
    -0.40
    Jîn
    -0.38
    Autoritní
    -0.37
     архивлан
    -0.36
    IUrlHelper
    -0.36
     nonUne
    -0.36
    甲
    -0.35
    Сылтамалар
    -0.34
    POSITIVE LOGITS
    fest
    0.65
    Fest
    0.60
     Composition
    0.60
     bulk
    0.59
     composition
    0.57
     Zusammensetzung
    0.57
    Bulk
    0.55
     Bulk
    0.54
    bulk
    0.54
     composición
    0.52
    Act Density 0.073%

    No Known Activations