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

    Neuronpedia

    INDEX
    Explanations

    titles, subtitles, or captions in a document

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.69
     Kitty
    -0.69
     scattering
    -0.66
    ibliography
    -0.65
     Annotations
    -0.64
    è¦ļéĨĴ
    -0.63
     Shattered
    -0.63
     doomed
    -0.63
     recl
    -0.62
    utterstock
    -0.62
    POSITIVE LOGITS
    -[
    0.95
    '"
    0.95
    there
    0.86
    sic
    0.86
    }"
    0.85
    .,"
    0.83
    "[
    0.81
    ?'"
    0.79
    ."[
    0.77
    ]"
    0.77
    Act Density 0.344%

    No Known Activations