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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in assistant or deputy roles

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

    assistant followed by job titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.65
    bcryptjs
    -0.59
     sää
    -0.57
    tinyos
    -0.57
    RectangleBorder
    -0.56
    GEBURTS
    -0.54
    énage
    -0.53
    tilhe
    -0.53
     meille
    -0.52
    出版年
    -0.52
    POSITIVE LOGITS
     Assistant
    0.84
    Assistant
    0.80
     assistant
    0.79
     ASSISTANT
    0.68
     Asst
    0.66
     Deputy
    0.57
     deputy
    0.56
    PUTY
    0.56
    assistant
    0.55
     Assistants
    0.54
    Act Density 0.010%

    No Known Activations