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

    Neuronpedia

    INDEX
    Explanations

    various types of quotation marks and punctuation that indicate dialogue or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    2
    -0.60
    </b>
    -0.57
    1
    -0.56
    3
    -0.56
    ↵↵
    -0.56
    *
    -0.55
    </h1>
    -0.55
    ­
    -0.54
    and
    -0.54
    <b>
    -0.53
    POSITIVE LOGITS
     '
    2.86
     ('
    2.44
     ‘
    2.37
    -'
    2.31
     '.
    2.30
     '/
    2.24
    ...'
    2.24
     '#
    2.22
     (‘
    2.18
     ,'
    2.17
    Act Density 0.243%

    No Known Activations