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

    Neuronpedia

    INDEX
    Explanations

    words related to medical complications

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.94
    berman
    -0.93
    bors
    -0.79
    entin
    -0.74
    amaru
    -0.73
    ers
    -0.72
    enium
    -0.72
    encer
    -0.71
    bour
    -0.70
    bor
    -0.70
    POSITIVE LOGITS
     complications
    1.10
     complication
    0.84
     arising
    0.79
     headaches
    0.77
     stemming
    0.76
     inconven
    0.75
     arise
    0.74
     incurred
    0.73
     plag
    0.71
    ascular
    0.71
    Act Density 0.015%

    No Known Activations