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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions that indicate a reference to parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auc
    -0.17
    erce
    -0.15
    hiba
    -0.14
    dub
    -0.14
    imens
    -0.14
    buat
    -0.14
    aç
    -0.14
     however
    -0.14
     thì
    -0.13
    pletion
    -0.13
    POSITIVE LOGITS
    aka
    0.16
    ÛĮÙĨÙĩ
    0.16
     Levy
    0.15
    ...)↵
    0.14
     Carlton
    0.14
    incinn
    0.13
     Neh
    0.13
    \<^
    0.13
     Busty
    0.13
    cas
    0.13
    Act Density 0.416%

    No Known Activations