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

    Neuronpedia

    INDEX
    Explanations

    words related to economic indicators, especially prices

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of prices, particularly in economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lich
    -0.85
    less
    -0.75
    ful
    -0.68
    ALLY
    -0.66
    proof
    -0.66
    lihood
    -0.66
    nel
    -0.65
    LESS
    -0.64
    iverse
    -0.64
    hood
    -0.63
    POSITIVE LOGITS
    paces
    1.35
    cape
    1.27
    heet
    1.27
    pring
    1.26
    cale
    1.23
    hare
    1.21
    poons
    1.21
    pace
    1.18
    avers
    1.05
    omething
    1.04
    Act Density 0.162%

    No Known Activations