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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities done at the expense of something or someone else

    oai_token-act-pair · gpt-3.5-turbo

    references to costs or consequences incurred by others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arre
    -0.65
     hairs
    -0.64
    oded
    -0.62
    ecided
    -0.62
    ruciating
    -0.62
    terday
    -0.62
    orious
    -0.60
    odes
    -0.60
    swick
    -0.59
    oggles
    -0.59
    POSITIVE LOGITS
     expense
    0.86
     detriment
    0.79
    士
    0.73
    ebook
    0.73
     altar
    0.73
    adle
    0.72
     disadvantage
    0.71
    hyde
    0.70
    ãĤ«
    0.70
    ARM
    0.69
    Act Density 0.034%

    No Known Activations