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

    Neuronpedia

    INDEX
    Explanations

    HTML elements and their attributes, particularly links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     http
    -0.59
    <eos>
    -0.57
     astore
    -0.54
     https
    -0.50
     toán
    -0.48
     or
    -0.48
    /
    -0.45
    цен
    -0.45
    klima
    -0.45
     Air
    -0.44
    POSITIVE LOGITS
    ="#"
    2.41
    ="#">
    1.78
    ="#"><
    1.65
    InjectAttribute
    1.61
    @[+][
    1.58
    WriteTagHelper
    1.18
     '\\;'
    1.14
     myſelf
    1.00
    EDEFAULT
    0.91
     actionPerformed
    0.88
    Act Density 0.012%

    No Known Activations