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

    Neuronpedia

    INDEX
    Explanations

    references to androids and robots, particularly in contexts discussing their functions and interactions

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

    robots and androids

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of robots, androids, artificial intelligence, or machine/robotic agents.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.67
    expandindo
    -0.62
    Rüyada
    -0.55
    Abitanti
    -0.54
    IsMutable
    -0.54
    Espèce
    -0.53
    chemise
    -0.51
    <?
    -0.50
    LabelTagHelper
    -0.49
    transQ
    -0.48
    POSITIVE LOGITS
     robot
    0.81
     Robot
    0.76
     robots
    0.75
     robo
    0.69
    robot
    0.68
    Robot
    0.67
     robotic
    0.67
    Robots
    0.65
     Robots
    0.65
    robo
    0.65
    Act Density 0.743%

    No Known Activations