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

    Neuronpedia

    INDEX
    Explanations

    references to costs and financial figures

    oai_token-act-pair · gpt-3.5-turbo

    references to costs or expenses associated with various items or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oration
    -0.72
    utenberg
    -0.71
    arding
    -0.70
    aucas
    -0.70
    ħĭ
    -0.69
    soType
    -0.69
    xual
    -0.67
    ixture
    -0.67
    committee
    -0.66
    Anth
    -0.66
    POSITIVE LOGITS
     dearly
    0.86
     upfront
    0.82
    ebook
    0.80
     bucks
    0.77
     apiece
    0.76
     USD
    0.76
     cents
    0.73
     Mum
    0.72
     (£
    0.72
     Hut
    0.72
    Act Density 0.136%

    No Known Activations