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

    Neuronpedia

    INDEX
    Explanations

    various types of quotation marks and parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NECT
    -0.16
    #
    -0.15
    ÐIJÑĢÑħÑĸв
    -0.15
     Ðŀдна
    -0.15
    (æ°´
    -0.14
    forming
    -0.14
    nila
    -0.14
    ngr
    -0.14
     Serialized
    -0.14
    HORT
    -0.14
    POSITIVE LOGITS
     automát
    0.18
    inson
    0.15
    anges
    0.15
    ffen
    0.15
    s
    0.14
    utc
    0.14
     correspondent
    0.14
     meisje
    0.14
    rette
    0.14
    ören
    0.14
    Act Density 0.067%

    No Known Activations