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

    Neuronpedia

    INDEX
    Explanations

    references to acknowledgments and expressions of gratitude in a formal context

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

    preceding personal service roles

    np_acts-logits-general · gemini-2.0-flash

    assistants and helpers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bapak
    -0.41
    dubbo
    -0.40
    出版年
    -0.40
     lawmaker
    -0.39
    uft
    -0.39
     BoxFit
    -0.39
    picasso
    -0.39
     topological
    -0.39
    instancetype
    -0.38
     مرجع
    -0.38
    POSITIVE LOGITS
     assistants
    1.22
     assistant
    1.07
     Assistants
    0.98
     housekeeper
    0.92
    assistant
    0.89
     staff
    0.88
     servant
    0.86
     servants
    0.86
     maids
    0.86
     helpers
    0.84
    Act Density 0.558%

    No Known Activations