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

    Neuronpedia

    INDEX
    Explanations

    questions or queries related to different topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    MER
    -0.71
    GV
    -0.62
     guiActiveUnfocused
    -0.62
     Habit
    -0.62
     saturation
    -0.61
     Rye
    -0.61
    emin
    -0.60
     Globe
    -0.60
    PORT
    -0.60
     Glob
    -0.60
    POSITIVE LOGITS
    soever
    1.18
    oping
    1.14
    ever
    1.11
     cares
    1.08
     else
    1.01
     knows
    0.99
    abouts
    0.98
    oped
    0.97
     cared
    0.92
    ppers
    0.85
    Act Density 0.104%

    No Known Activations