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

    Neuronpedia

    INDEX
    Explanations

    references to background information or context in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     réguli
    -0.84
     Poem
    -0.77
    baye
    -0.77
     goû
    -0.73
    matchCondition
    -0.73
    ⮕
    -0.73
     sexuales
    -0.72
     Trotter
    -0.70
     réunis
    -0.69
    ModelAdmin
    -0.69
    POSITIVE LOGITS
     background
    1.80
     Background
    1.60
     backgrounds
    1.59
    Background
    1.51
    background
    1.45
     BACKGROUND
    1.37
    BACKGROUND
    1.34
    背景
    1.14
    bkg
    1.05
    Bg
    1.04
    Act Density 0.065%

    No Known Activations