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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks and phrases indicating speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guill
    -0.68
     Hel
    -0.66
     esqu
    -0.66
     Deane
    -0.62
    StringTokenizer
    -0.60
    øver
    -0.58
     Blackburn
    -0.57
     azar
    -0.57
     Laing
    -0.56
     Para
    -0.56
    POSITIVE LOGITS
     ’
    1.46
     ”
    1.14
     »
    0.93
     ”,
    0.92
    $",
    0.92
    ()")
    0.87
     &=&
    0.83
    ’’
    0.83
     ”.
    0.80
    }-*/;
    0.80
    Act Density 0.184%

    No Known Activations