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

    Neuronpedia

    INDEX
    Explanations

    references to proper dining etiquette and utensil usage

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

    Followed by articles or prepositions

    np_acts-logits-general · gemini-2.0-flash

    passing items or directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suffice
    -0.45
     Treff
    -0.44
    YOND
    -0.44
    \{\\
    -0.42
    xed
    -0.39
     improvised
    -0.38
    Rhestr
    -0.38
     slapped
    -0.38
     Tapia
    -0.38
     outrage
    -0.38
    POSITIVE LOGITS
     Wikimedijinoj
    0.65
     comuniques
    0.65
     EconPapers
    0.62
    CloseOperation
    0.60
     Мексичка
    0.57
     мәкал
    0.56
    хьтан
    0.52
    تقاوى
    0.50
    тьяна
    0.49
    GEBURTSDATUM
    0.49
    Act Density 0.755%

    No Known Activations