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

    Neuronpedia

    INDEX
    Explanations

    frequent articles that serve as function words in the text

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

    the followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.75
     estekak
    -0.74
    hyrchwyd
    -0.67
     فريبيس
    -0.65
    脚注の使い方
    -0.62
    Бахар
    -0.61
     autorytatywna
    -0.60
    pecabe
    -0.60
     tapaht
    -0.59
    ьаж
    -0.57
    POSITIVE LOGITS
     dem
    0.38
    把
    0.35
    CREAT
    0.34
     the
    0.34
     Brunner
    0.34
    >):
    0.33
     las
    0.33
    CC
    0.33
     Fü
    0.33
    ])))
    0.33
    Act Density 0.089%

    No Known Activations