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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "by" indicating authorship or agency in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poon
    -0.15
    alom
    -0.15
     Crossing
    -0.14
    rug
    -0.14
    undi
    -0.14
    inally
    -0.14
    poons
    -0.13
    hos
    -0.13
    ãĥ¼ãĥķ
    -0.13
    _POINTER
    -0.13
    POSITIVE LOGITS
     itself
    0.17
    isi
    0.17
    odb
    0.15
    /of
    0.15
    amba
    0.14
    Į¨
    0.14
     chance
    0.14
    vre
    0.14
     definition
    0.14
    ali
    0.14
    Act Density 0.044%

    No Known Activations