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

    Neuronpedia

    INDEX
    Explanations

    phrases related to welfare policies and state intervention

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.68
    terday
    -0.67
     Zheng
    -0.65
    ergy
    -0.65
    utm
    -0.64
     Frog
    -0.63
    inx
    -0.63
     SX
    -0.63
    nings
    -0.61
     Brun
    -0.60
    POSITIVE LOGITS
    elfare
    1.08
     recipients
    1.05
     welfare
    0.96
     beneficiaries
    0.93
    ocrats
    0.86
     reform
    0.86
     queens
    0.85
    benefit
    0.84
     programs
    0.81
     agencies
    0.81
    Act Density 0.015%

    No Known Activations