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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "by" indicating authorship or agency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alm
    -0.16
    ordo
    -0.16
    ussen
    -0.14
    cad
    -0.14
    upert
    -0.14
    ouns
    -0.14
     Moreno
    -0.14
    CP
    -0.14
    ensi
    -0.13
    rai
    -0.13
    POSITIVE LOGITS
    æīķ
    0.14
    stantiate
    0.14
    Æ°á»Łng
    0.14
    ç©´
    0.14
    rek
    0.14
    ÏĩεδÏĮν
    0.14
    CCCCCC
    0.13
    gether
    0.13
    浩
    0.13
    tlement
    0.13
    Act Density 0.014%

    No Known Activations