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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exposure to various substances or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to exposure to various substances or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.74
    ataka
    -0.71
    maker
    -0.70
    ricting
    -0.69
    starter
    -0.68
    notations
    -0.67
    wise
    -0.67
    ardon
    -0.66
    etary
    -0.64
    ries
    -0.64
    POSITIVE LOGITS
    ibilities
    0.88
    é¾
    0.85
     Exposure
    0.83
     weaknesses
    0.78
    ibly
    0.73
    holes
    0.73
     Breach
    0.73
    в
    0.72
    ibility
    0.70
    iltr
    0.70
    Act Density 0.046%

    No Known Activations