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

    Neuronpedia

    INDEX
    Explanations

    mentions of welfare programs or related social assistance initiatives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihnachten
    -0.55
    Pand
    -0.54
     Pand
    -0.54
     Montague
    -0.49
     Lichten
    -0.47
     McInt
    -0.47
     Morg
    -0.46
     Vat
    -0.46
     Schn
    -0.46
     Schlu
    -0.46
    POSITIVE LOGITS
     welfare
    1.14
     Welfare
    1.14
    welfare
    1.10
    Welfare
    1.07
     WELFARE
    0.96
    elfare
    0.92
     Wells
    0.76
     Wel
    0.73
    Wells
    0.69
     wel
    0.68
    Act Density 0.167%

    No Known Activations