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

    Neuronpedia

    INDEX
    Explanations

    words relating to the concept of exposure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exposure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aws
    -0.71
    assian
    -0.69
    rones
    -0.65
    jas
    -0.62
    rolley
    -0.62
    hips
    -0.60
    oris
    -0.60
    ran
    -0.60
    ophers
    -0.59
    ŃĶ
    -0.58
    POSITIVE LOGITS
     Exposure
    1.23
     exposure
    1.09
     exposures
    0.95
    çīĪ
    0.86
     destro
    0.83
    ibilities
    0.79
    ibl
    0.79
    quished
    0.78
    itaire
    0.77
     vulner
    0.76
    Act Density 0.008%

    No Known Activations