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

    Neuronpedia

    INDEX
    Explanations

    words related to severe health risks or adverse effects in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sclerosis
    -0.16
    ActivityIndicatorView
    -0.16
     deficit
    -0.15
    criptor
    -0.15
    KeySpec
    -0.14
     Brew
    -0.13
    cdecl
    -0.13
    ullo
    -0.13
    arus
    -0.13
     Diagnosis
    -0.13
    POSITIVE LOGITS
     adverse
    0.42
     side
    0.42
     Side
    0.36
     reactions
    0.35
     reaction
    0.32
    Side
    0.30
     SIDE
    0.29
    _side
    0.27
     allergic
    0.27
    side
    0.27
    Act Density 0.165%

    No Known Activations