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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to the healthcare system and its impact on various populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.76
    manship
    -0.74
    tackle
    -0.65
    washing
    -0.65
    forward
    -0.64
    wcsstore
    -0.64
     symmetry
    -0.63
    Episode
    -0.63
    assetsadobe
    -0.61
    imposed
    -0.61
    POSITIVE LOGITS
     poorest
    1.49
     wealthiest
    1.38
     masses
    1.33
     elderly
    1.27
     unemployed
    1.27
     disadvantaged
    1.18
     needy
    1.17
     populace
    1.16
     richest
    1.15
     oppressed
    1.14
    Act Density 0.216%

    No Known Activations