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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks and periods, indicating transitions and emphasis in dialogue or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ';
    -0.86
     \\
    -0.79
     Efq
    -0.76
     Jefus
    -0.76
     Senhora
    -0.74
     ſte
    -0.73
     ſy
    -0.72
    BibitemShut
    -0.72
     =>
    -0.71
    ToScroll
    -0.70
    POSITIVE LOGITS
     (
    0.80
    ・「
    0.73
     “
    0.71
     (“
    0.70
    ("
    0.68
     مشين
    0.66
    ，“
    0.65
     ("
    0.64
    otheses
    0.63
     "
    0.63
    Act Density 0.543%

    No Known Activations