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

    Neuronpedia

    INDEX
    Explanations

    specific visual elements or labels in graphical representations or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    titleMargin
    -0.68
    pagestyle
    -0.63
    riwal
    -0.62
    AsUp
    -0.58
     resourceCulture
    -0.57
    hæng
    -0.57
     Italijanski
    -0.56
    AnchorStyles
    -0.55
    knecht
    -0.53
    nościo
    -0.53
    POSITIVE LOGITS
    while
    0.55
     mentre
    0.54
     للاسماء
    0.52
     <<<<<<<<<<<<<<
    0.52
    whereas
    0.49
     while
    0.49
     terwijl
    0.48
     Sedangkan
    0.47
     tandis
    0.47
     ενώ
    0.46
    Act Density 0.795%

    No Known Activations