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

    Neuronpedia

    INDEX
    Explanations

    linguistic structures and punctuation patterns indicating complex or emphatic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ->__
    -0.15
    ceptar
    -0.14
    pp
    -0.14
    enco
    -0.14
    ippi
    -0.14
    OutOfBounds
    -0.14
     torino
    -0.13
    ÙĪÙħÛĮ
    -0.13
    omi
    -0.13
    stown
    -0.13
    POSITIVE LOGITS
    chter
    0.16
     Pes
    0.15
    gency
    0.15
    ebra
    0.14
    гл
    0.14
     an
    0.14
    FOUND
    0.14
    uez
    0.14
    ez
    0.14
    lap
    0.13
    Act Density 0.162%

    No Known Activations