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

    Neuronpedia

    INDEX
    Explanations

    prices or costs in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with monetary amounts or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.75
     antioxid
    -0.70
     firsthand
    -0.68
     spont
    -0.65
     advoc
    -0.62
     seminal
    -0.62
     strugg
    -0.61
     resemb
    -0.60
     behavi
    -0.59
     dysph
    -0.59
    POSITIVE LOGITS
    000
    1.83
    500
    1.80
    600
    1.61
    700
    1.59
    800
    1.59
    750
    1.55
    200
    1.55
    250
    1.52
    950
    1.52
    400
    1.52
    Act Density 0.043%

    No Known Activations