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

    Neuronpedia

    INDEX
    Explanations

    references to financial transactions or remuneration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    paying attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trekken
    -0.56
    ähteet
    -0.56
     Kräfte
    -0.55
     Munro
    -0.52
     McNeil
    -0.52
     desideri
    -0.52
     förslag
    -0.52
     pulp
    -0.51
     Vorschlag
    -0.51
     Christensen
    -0.50
    POSITIVE LOGITS
     paying
    1.61
     Paying
    1.59
    Paying
    1.56
    paying
    1.55
     payer
    0.96
     paid
    0.91
    payer
    0.88
     payers
    0.85
     Paid
    0.85
    Paid
    0.84
    Act Density 0.003%

    No Known Activations