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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific structural markers or identifiers in text, often related to URLs and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.84
    tagHelperRunner
    -0.79
    AddHtmlAttribute
    -0.73
    lynol
    -0.69
    Enllaces
    -0.67
    Sucesor
    -0.66
     Sebab
    -0.64
    ^(@)
    -0.62
    djangoproject
    -0.60
     cherchés
    -0.60
    POSITIVE LOGITS
    ↵↵
    0.59
    HasAnnotation
    0.58
    <eos>
    0.50
    “.
    0.50
     vapeur
    0.49
    posedge
    0.48
     paille
    0.47
    prefixer
    0.47
    preventDefault
    0.47
     hâte
    0.47
    Act Density 0.012%

    No Known Activations