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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exposure to various substances

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of exposure, particularly to harmful substances or environmental factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reme
    -0.80
    rones
    -0.76
    ries
    -0.69
    rolley
    -0.68
    ian
    -0.68
    rup
    -0.68
    rolog
    -0.67
     Rao
    -0.67
    ricting
    -0.67
    baum
    -0.66
    POSITIVE LOGITS
     Exposure
    0.91
    ibilities
    0.83
     exposure
    0.75
    çīĪ
    0.73
    PsyNetMessage
    0.73
    ibility
    0.72
    в
    0.72
    xual
    0.69
    Experience
    0.69
    801
    0.68
    Act Density 0.018%

    No Known Activations