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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    oai_token-act-pair · gpt-3.5-turbo

    HTML tags and structural elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.76
     whist
    -0.69
    itives
    -0.67
    eer
    -0.66
     wiret
    -0.64
     Immunity
    -0.63
     Guant
    -0.63
     somew
    -0.63
     gag
    -0.62
     deleg
    -0.62
    POSITIVE LOGITS
    ":{"
    0.85
    span
    0.83
    "><
    0.81
    ><
    0.80
    Premium
    0.77
    !--
    0.77
    input
    0.75
    TIT
    0.74
    dimension
    0.74
    title
    0.73
    Act Density 0.019%

    No Known Activations