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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and related punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.44
    </blockquote>
    -0.41
    addContainerGap
    -0.39
     quite
    -0.38
    alış
    -0.38
     lucru
    -0.37
     }}}
    -0.36
     aluguel
    -0.36
    ’.
    -0.36
     papild
    -0.36
    POSITIVE LOGITS
     utafitiHapana
    0.86
    깥
    0.86
     שוליים
    0.83
    AutoField
    0.81
     또는
    0.80
    apimachinery
    0.79
    
    0.79
     Мексичка
    0.79
    IntoConstraints
    0.79
    ipheral
    0.77
    Act Density 0.548%

    No Known Activations