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

    Neuronpedia

    INDEX
    Explanations

    words related to potential side effects in medication or medical treatment

    oai_token-act-pair · gpt-3.5-turbo

    references to side effects, particularly adverse health effects associated with medications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atters
    -0.85
    Completed
    -0.79
    igsaw
    -0.71
     istg
    -0.70
    lex
    -0.69
    Tumblr
    -0.69
    ropolitan
    -0.68
    ilts
    -0.68
    Blocks
    -0.66
     pivot
    -0.65
    POSITIVE LOGITS
    effects
    1.10
     consequences
    1.04
     effects
    0.97
     repercussions
    0.93
     adverse
    0.93
     symptoms
    0.93
     associated
    0.92
     treatments
    0.91
     diseases
    0.90
     toxicity
    0.88
    Act Density 0.141%

    No Known Activations