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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     threatened
    -0.15
     matching
    -0.15
     needed
    -0.14
     tainted
    -0.14
    805
    -0.14
    _seconds
    -0.14
     disturbed
    -0.14
    620
    -0.14
     adverse
    -0.13
    eker
    -0.13
    POSITIVE LOGITS
     caused
    0.22
     treat
    0.21
     prevent
    0.20
     CAUSED
    0.17
     incur
    0.17
    prevent
    0.17
    ama
    0.17
     cured
    0.17
     reversible
    0.16
     worse
    0.16
    Act Density 0.255%

    No Known Activations