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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and other punctuation that indicates direct speech or citation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.60
     cardiaque
    -0.58
     déclar
    -0.57
    Weakness
    -0.56
    faz
    -0.51
     químicas
    -0.51
     démission
    -0.50
     secours
    -0.50
     Extinction
    -0.49
     Torna
    -0.49
    POSITIVE LOGITS
     “
    0.81
     ‘
    0.80
    =$("#
    0.78
    ISODE
    0.74
     Мексичка
    0.73
     „
    0.73
     ‚
    0.71
    %;
    0.68
     sogen
    0.67
     special
    0.67
    Act Density 0.179%

    No Known Activations