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

    Neuronpedia

    INDEX
    Explanations

    references to income levels and financial disparities

    oai_token-act-pair · gpt-3.5-turbo

    references to income levels and economic statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wilson
    -0.78
    film
    -0.76
    anim
    -0.72
    flix
    -0.72
    CTV
    -0.70
    iov
    -0.70
    rique
    -0.69
     Camer
    -0.68
    journal
    -0.68
    gif
    -0.67
    POSITIVE LOGITS
     lowest
    1.58
     lower
    1.47
     lows
    1.44
     higher
    1.35
    higher
    1.35
    Hig
    1.34
    highest
    1.32
    levels
    1.31
     tiers
    1.31
     upper
    1.29
    Act Density 0.350%

    No Known Activations