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

    Neuronpedia

    INDEX
    Explanations

    key metrics and outcomes relevant to academic research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.88
     reaſon
    -0.75
     pleaſure
    -0.74
     reafon
    -0.72
     Efq
    -0.71
     poffe
    -0.69
    ArrowToggle
    -0.69
     fevere
    -0.68
     المعيارى
    -0.68
     ſtate
    -0.67
    POSITIVE LOGITS
     "..\..\..\
    0.52
     مقالات
    0.50
     "..\..\
    0.49
     diatas
    0.45
    løs
    0.45
    出来た
    0.45
     mengikut
    0.45
     cref
    0.44
     tajam
    0.44
    assertNot
    0.44
    Act Density 0.018%

    No Known Activations