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

    Neuronpedia

    INDEX
    Explanations

    indicators of risk and vulnerability in health-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cka
    -0.14
    RESSION
    -0.14
    bedo
    -0.14
    ESC
    -0.14
    ause
    -0.13
    oyo
    -0.13
    .Debugger
    -0.13
    plits
    -0.13
    uj
    -0.13
    ordion
    -0.13
    POSITIVE LOGITS
     risk
    0.90
     risks
    0.77
     Risk
    0.73
    risk
    0.72
    Risk
    0.68
    -risk
    0.63
     Ris
    0.60
    é£İéĻ©
    0.60
     risking
    0.54
     risky
    0.48
    Act Density 0.247%

    No Known Activations