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

    Neuronpedia

    INDEX
    Explanations

    references to guidelines or criteria for evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Демографія
    -0.83
    ⓧ
    -0.82
    Nuorodos
    -0.66
     дописавши
    -0.64
     ""],
    -0.63
     Préférences
    -0.62
    AndEndTag
    -0.61
     препратки
    -0.60
     Wikispecies
    -0.60
     Wicidata
    -0.59
    POSITIVE LOGITS
     المعيارى
    0.63
    zeptember
    0.62
    GraphicsUnit
    0.61
    ėk
    0.58
     للاسماء
    0.57
     done
    0.56
     BorderSide
    0.56
    enumi
    0.55
     adesivos
    0.54
    iomanip
    0.54
    Act Density 0.303%

    No Known Activations