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

    Neuronpedia

    INDEX
    Explanations

    terms related to robots and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.90
    InstanceState
    -0.83
    UnsafeEnabled
    -0.80
     Fathers
    -0.75
    ensement
    -0.75
    __':
    -0.74
     Haring
    -0.74
     ECL
    -0.73
     onPostExecute
    -0.72
    thalene
    -0.71
    POSITIVE LOGITS
     robot
    1.53
     robots
    1.41
     Robot
    1.36
    robot
    1.27
     robotic
    1.23
    robots
    1.23
    Robot
    1.22
    Robots
    1.21
     Robots
    1.21
     Bot
    1.15
    Act Density 0.286%

    No Known Activations