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

    Neuronpedia

    INDEX
    Explanations

    terms related to government welfare programs

    oai_token-act-pair · gpt-3.5-turbo

    references to welfare programs and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.72
     Ou
    -0.68
    imb
    -0.64
     Brun
    -0.63
    ergy
    -0.62
    quart
    -0.62
     Sie
    -0.61
    heter
    -0.60
    semble
    -0.60
     Hole
    -0.59
    POSITIVE LOGITS
    elfare
    1.21
     welfare
    1.06
     recipients
    0.95
     entitle
    0.91
    benefit
    0.90
     Welfare
    0.86
     reform
    0.86
     beneficiaries
    0.83
    ocrats
    0.81
    ega
    0.80
    Act Density 0.014%

    No Known Activations