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

    Neuronpedia

    INDEX
    Explanations

    references to preferences or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Souhaitez
    -0.62
     للمعارف
    -0.52
     culturelles
    -0.49
     spirituale
    -0.48
    :✨
    -0.48
    Surprised
    -0.48
    łecz
    -0.47
     ivelany
    -0.47
     culturale
    -0.46
     quitte
    -0.46
    POSITIVE LOGITS
    MemoryWarning
    0.71
     viewDidLoad
    0.68
    cillor
    0.65
     CURIAM
    0.64
    ianum
    0.63
    ofition
    0.63
    ratulations
    0.61
    umque
    0.60
    othesis
    0.60
    ghis
    0.59
    Act Density 0.001%

    No Known Activations