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

    Neuronpedia

    INDEX
    Explanations

    names of authors in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieten
    -0.15
    ë£Į
    -0.14
    raj
    -0.14
    oute
    -0.14
    iforn
    -0.14
    xing
    -0.14
    wang
    -0.13
    .gdx
    -0.13
    proto
    -0.13
    ån
    -0.13
    POSITIVE LOGITS
    Echo
    0.14
    ATAR
    0.14
    okane
    0.13
    gin
    0.13
    993
    0.13
    ãģĩ
    0.13
    ysa
    0.13
    845
    0.12
     Fram
    0.12
    AJOR
    0.12
    Act Density 0.003%

    No Known Activations