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

    Neuronpedia

    INDEX
    Explanations

    statements that contain praise or positive descriptors about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.68
    verwijspagina
    -0.64
     ویکی‌پدی
    -0.62
     समीक्षाएं
    -0.58
     hObject
    -0.58
     समीक्षाओं
    -0.56
     onPage
    -0.55
    Diwedd
    -0.54
    rénées
    -0.51
     ModelExpression
    -0.49
    POSITIVE LOGITS
    ividual
    0.63
    litude
    0.62
    neos
    0.62
     non
    0.60
    TabStop
    0.59
    UseVisualStyle
    0.59
    WAUKEE
    0.58
    surate
    0.58
     dominant
    0.58
    plevel
    0.57
    Act Density 0.248%

    No Known Activations