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

    Neuronpedia

    INDEX
    Explanations

    terminology related to health risks and patient assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    risk-related words and concepts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    words and phrases indicating potential danger, hazard, or adverse outcomes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    oneofs
    -0.38
    gonic
    -0.34
    UrlResolution
    -0.32
     شاه
    -0.30
     TextEditing
    -0.30
     Cot
    -0.29
    createStatement
    -0.29
     HasFactory
    -0.29
     StringTokenizer
    -0.29
    cshtml
    -0.28
    POSITIVE LOGITS
     risk
    3.16
    risk
    2.70
     risks
    2.67
     Risk
    2.61
    Risk
    2.59
     RISK
    2.44
     Risiko
    2.27
    RISK
    2.27
    risks
    2.25
     Risks
    2.23
    Act Density 0.624%

    No Known Activations