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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing doubts or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of ambivalence or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gans
    -0.66
    FTWARE
    -0.65
     benefited
    -0.65
    glass
    -0.64
    ships
    -0.61
    fill
    -0.60
    visors
    -0.59
    Russ
    -0.58
    thumbnails
    -0.57
    boats
    -0.57
    POSITIVE LOGITS
     least
    1.27
     times
    0.94
    roph
    0.92
    onement
    0.90
    abase
    0.89
    yp
    0.86
     halftime
    0.85
     home
    0.82
    ention
    0.82
     conception
    0.79
    Act Density 0.234%

    No Known Activations