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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to events, particularly focused on counts of people, losses, or financial statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.71
    odox
    -0.71
    bley
    -0.66
    slow
    -0.66
    bye
    -0.63
    requently
    -0.61
    cients
    -0.60
    Rap
    -0.59
    zan
    -0.59
     Stras
    -0.59
    POSITIVE LOGITS
     totals
    0.83
     liabilities
    0.83
    urden
    0.82
     total
    0.81
     expenditures
    0.79
     totaled
    0.76
     expenditure
    0.74
    total
    0.73
     allowable
    0.73
     output
    0.72
    Act Density 0.078%

    No Known Activations