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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and their usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.93
    findpost
    -0.93
    ."),
    -0.90
     podjela
    -0.89
     propOrder
    -0.86
     Lutz
    -0.86
    ]--;
    -0.86
    İstinadlar
    -0.84
     للاسماء
    -0.84
    %)$
    -0.82
    POSITIVE LOGITS
     «
    2.09
    «
    1.92
     («
    1.67
    .«
    1.33
    ««
    1.29
     «<
    1.26
     „
    1.19
    »
    1.12
    „
    1.08
    ,«
    1.06
    Act Density 0.232%

    No Known Activations