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

    Neuronpedia

    INDEX
    Explanations

    instances where the term "same" or similar comparative concepts are referenced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abetes
    -0.75
    yntaxException
    -0.72
    HtmlAttribute
    -0.70
    -0.69
    beitung
    -0.65
     Waray
    -0.62
    />";
    -0.61
    setupUi
    -0.61
    ropoda
    -0.60
    soever
    -0.59
    POSITIVE LOGITS
     same
    0.88
    same
    0.79
     Same
    0.68
    Same
    0.68
    SAME
    0.64
     SAME
    0.62
     than
    0.61
     hetzelfde
    0.55
     selben
    0.54
     samme
    0.53
    Act Density 0.285%

    No Known Activations