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

    Neuronpedia

    INDEX
    Explanations

    words related to social welfare programs or benefits

    oai_token-act-pair · gpt-3.5-turbo

    references to welfare and related social programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.77
    ergy
    -0.75
     Brun
    -0.67
    ombs
    -0.66
    itars
    -0.64
    inx
    -0.64
     Zheng
    -0.64
    aque
    -0.63
    beit
    -0.62
     Frog
    -0.60
    POSITIVE LOGITS
    elfare
    1.10
     welfare
    0.96
     recipients
    0.94
     reform
    0.86
     beneficiaries
    0.82
    benefit
    0.80
     Welfare
    0.80
     entitle
    0.79
     queens
    0.76
    fare
    0.76
    Act Density 0.022%

    No Known Activations