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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation-related text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    #+#
    -1.04
    :+:
    -0.89
    riceps
    -0.88
    LookAnd
    -0.82
    ########.
    -0.81
     betweenstory
    -0.81
     AssemblyCompany
    -0.78
     kasarigan
    -0.75
    orianCalendar
    -0.74
     >=",
    -0.73
    POSITIVE LOGITS
    پیوند
    0.56
     sonora
    0.49
     invester
    0.46
     وث
    0.46
     tour
    0.45
     cung
    0.44
     comer
    0.44
    hidup
    0.44
    Shell
    0.43
    Quotes
    0.43
    Act Density 0.008%

    No Known Activations