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

    Neuronpedia

    INDEX
    Explanations

    phrases related to captions or advertisement messages

    oai_token-act-pair · gpt-3.5-turbo

    references to content titles or captions associated with Netflix shows or movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.79
    isSpecial
    -0.77
    oreAnd
    -0.75
    aditional
    -0.75
     oun
    -0.72
    Ă
    -0.71
    À
    -0.71
    ò
    -0.71
    ą
    -0.71
    ö
    -0.70
    POSITIVE LOGITS
     caption
    0.82
     Gallery
    0.74
     Caption
    0.71
     Sketch
    0.68
     Photos
    0.67
     embed
    0.66
     slideshow
    0.65
     attm
    0.65
     guiName
    0.64
     Prev
    0.64
    Act Density 0.038%

    No Known Activations