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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to control flow and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ControllerBase
    -0.54
     ")";
    -0.54
     EconPapers
    -0.52
     }}"></
    -0.49
     Ride
    -0.49
     puissiez
    -0.48
     tena
    -0.48
    Ride
    -0.47
     ")");
    -0.46
    MLLoader
    -0.46
    POSITIVE LOGITS
    arrête
    0.62
     quit
    0.61
     termination
    0.60
     arrêter
    0.60
     terminates
    0.59
     exit
    0.59
     terminate
    0.59
     irgendwann
    0.59
     quits
    0.59
    contentLoaded
    0.58
    Act Density 0.211%

    No Known Activations