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

    Neuronpedia

    INDEX
    Explanations

    words related to health risks and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to risk factors for various health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.87
     Remastered
    -0.79
    ilver
    -0.77
    elf
    -0.77
    SEC
    -0.69
     Seasons
    -0.68
    MX
    -0.66
    Nap
    -0.65
    endment
    -0.64
    steel
    -0.63
    POSITIVE LOGITS
     factors
    0.88
     allele
    0.82
     factor
    0.81
     mortality
    0.76
     predis
    0.73
     Factors
    0.73
    ogenic
    0.72
     carcin
    0.72
     reduction
    0.72
    busters
    0.70
    Act Density 0.034%

    No Known Activations