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

    Neuronpedia

    INDEX
    Explanations

    references to concepts or terms that are introduced as "so-called" or defined in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     that
    -0.46
    тивы
    -0.44
     Bruch
    -0.43
    дыду
    -0.43
     pytest
    -0.43
     trouverez
    -0.42
    др
    -0.40
     elé
    -0.40
    Abstra
    -0.39
     lettore
    -0.39
    POSITIVE LOGITS
     sogenannte
    0.98
     sogenannten
    0.97
     tzw
    0.88
     vPvB
    0.80
     sogen
    0.79
    ImageContext
    0.79
     ''}
    0.78
     '>=
    0.77
     “
    0.77
    いわゆる
    0.75
    Act Density 0.443%

    No Known Activations