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

    Neuronpedia

    INDEX
    Explanations

    the use of quotation marks or apostrophes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Xna
    -0.92
    ContentAlignment
    -0.83
    ochond
    -0.78
     CONS
    -0.77
    {}".
    -0.75
     komp
    -0.74
     Cochrane
    -0.73
    Vidite
    -0.71
    Xd
    -0.70
    UpInside
    -0.66
    POSITIVE LOGITS
     ‚
    1.28
     ‘
    1.19
     (‘
    1.01
    ‗
    0.96
     ’
    0.96
    ‘
    0.94
     '
    0.93
    (‘
    0.92
    、『
    0.89
    =’
    0.85
    Act Density 0.102%

    No Known Activations