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

    Neuronpedia

    INDEX
    Explanations

    references to people and their attributes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.63
     estimés
    -0.59
     defStyleAttr
    -0.58
     Exacts
    -0.57
     doGet
    -0.57
     pector
    -0.55
     hjel
    -0.55
    __.__
    -0.54
     termica
    -0.53
     meille
    -0.52
    POSITIVE LOGITS
     who
    1.06
     whose
    0.80
    whose
    0.72
    Whose
    0.72
     quien
    0.71
     quem
    0.70
    who
    0.70
     Whose
    0.69
    팎
    0.68
     Who
    0.68
    Act Density 0.419%

    No Known Activations