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

    Neuronpedia

    INDEX
    Explanations

    mention of various illnesses or health conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of illness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bloc
    -0.65
    bour
    -0.62
    reme
    -0.62
    de
    -0.62
     ranger
    -0.62
    Polit
    -0.61
     compr
    -0.61
     tentative
    -0.59
    bors
    -0.58
    teen
    -0.57
    POSITIVE LOGITS
     illness
    1.02
    ptoms
    0.91
     illnesses
    0.90
    imei
    0.84
     outbreak
    0.84
     outbreaks
    0.81
     sickness
    0.79
    igue
    0.79
    nesses
    0.78
    ousing
    0.77
    Act Density 0.012%

    No Known Activations