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

    Neuronpedia

    INDEX
    Explanations

    sections marked with special characters or formatting indicators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    medriver
    -0.67
     Melayu
    -0.52
     colspan
    -0.49
    eln
    -0.47
    Me
    -0.47
    к
    -0.46
    رام
    -0.46
     Me
    -0.45
     CSE
    -0.45
     HOM
    -0.45
    POSITIVE LOGITS
     ~~~
    1.15
    ~~~
    1.11
    UnusedPrivate
    0.92
     سكانية
    0.83
    HtmlAttribute
    0.77
    τευ
    0.74
     Wib
    0.73
     Monfieur
    0.73
    expandindo
    0.73
     Viana
    0.71
    Act Density 0.003%

    No Known Activations