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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal or cultural norms

    oai_token-act-pair · gpt-3.5-turbo

    references to societal or cultural norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Savings
    -0.76
     Investments
    -0.68
    afia
    -0.65
    ulhu
    -0.64
    eries
    -0.64
     Sear
    -0.63
     Giles
    -0.63
    ierce
    -0.61
    azar
    -0.61
     County
    -0.60
    POSITIVE LOGITS
     norm
    3.95
    norm
    2.28
    Norm
    1.88
     Norm
    1.73
     norms
    1.72
     normal
    1.49
    normal
    1.44
     normative
    1.28
    Normal
    1.25
     horizont
    1.17
    Act Density 0.008%

    No Known Activations