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

    Neuronpedia

    INDEX
    Explanations

    numbers representing monetary values

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating monetary amounts or costs associated with items or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.80
    \<
    -0.69
    soType
    -0.69
    hao
    -0.67
    Occup
    -0.67
    mare
    -0.66
    Lou
    -0.66
    LAB
    -0.64
    Press
    -0.63
    odox
    -0.63
    POSITIVE LOGITS
    geries
    1.24
    gery
    1.12
    bidden
    1.12
     example
    1.06
     instance
    1.03
    gotten
    0.98
    ked
    0.93
     starters
    0.93
     each
    0.89
     purposes
    0.86
    Act Density 0.157%

    No Known Activations