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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of riding or the act of riding itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ted
    -0.18
    drawing
    -0.17
    mie
    -0.16
    á»Ĺ
    -0.16
    xing
    -0.16
    ught
    -0.16
    Histogram
    -0.15
    loe
    -0.15
    atos
    -0.15
    tee
    -0.15
    POSITIVE LOGITS
     shotgun
    0.24
     ride
    0.23
     rides
    0.21
    /dr
    0.20
     Shotgun
    0.20
     horses
    0.20
    hare
    0.19
     Ride
    0.19
     riders
    0.19
     rough
    0.19
    Act Density 0.018%

    No Known Activations