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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "reported"

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

    reported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.54
     Belf
    -0.52
     personalization
    -0.50
     Swartz
    -0.50
    mast
    -0.48
     McP
    -0.47
    ígen
    -0.46
    Vac
    -0.46
    isTrue
    -0.46
     WASTE
    -0.45
    POSITIVE LOGITS
     reported
    2.02
    reported
    1.74
     Reported
    1.61
    Reported
    1.56
     dilaporkan
    1.11
     reporting
    1.10
     reports
    1.05
     reporte
    1.04
     Reporting
    0.96
     report
    0.94
    Act Density 0.019%

    No Known Activations