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

    Neuronpedia

    INDEX
    Explanations

    conversational cues indicating uncertainty or requests for confirmation

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

    ok with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.73
     autorytatywna
    -0.68
    تقاوى
    -0.64
    parsedMessage
    -0.64
     transfieras
    -0.62
    Jîn
    -0.61
     disambiguazione
    -0.60
     ویکی‌آمباردا
    -0.60
    ècie
    -0.60
    Datuak
    -0.59
    POSITIVE LOGITS
    essentiel
    0.30
    asztok
    0.29
     Gäste
    0.29
     Flücht
    0.28
     guest
    0.28
    heça
    0.28
     yolu
    0.28
     afternoon
    0.28
    MENAFN
    0.28
     beseech
    0.26
    Act Density 0.090%

    No Known Activations