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

    Neuronpedia

    INDEX
    Explanations

    occurrences of "DOCTYPE" and related HTML document structure terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jud
    -0.16
    ston
    -0.15
    ãĤº
    -0.15
    .bd
    -0.15
    tog
    -0.14
    stance
    -0.14
    ooky
    -0.14
    ritten
    -0.13
    ieving
    -0.13
    Ùĩ
    -0.13
    POSITIVE LOGITS
    kova
    0.16
    quiv
    0.15
     specifier
    0.14
    lashes
    0.14
    lam
    0.14
     Zucker
    0.14
    orus
    0.14
    éłĺ
    0.13
    é¢Ĩ
    0.13
    paces
    0.13
    Act Density 0.001%

    No Known Activations