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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.85
    يميديا
    -0.82
    mphony
    -0.81
     AssemblyVersion
    -0.80
    ^(@)
    -0.80
     saites
    -0.80
    adpleegd
    -0.79
    #+#
    -0.78
     Anfitrión
    -0.77
    WebServlet
    -0.75
    POSITIVE LOGITS
    <eos>
    0.48
    ="@+
    0.47
    tek
    0.41
    #
    0.39
       
    0.38
    ulitis
    0.38
    ↵↵
    0.38
                                   
    0.38
     zu
    0.36
     "
    0.36
    Act Density 0.711%

    No Known Activations