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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dür
    -0.16
    igne
    -0.15
    orrent
    -0.15
    άκ
    -0.15
    elson
    -0.14
    sed
    -0.14
    uring
    -0.14
    ronics
    -0.13
    commercial
    -0.13
    work
    -0.13
    POSITIVE LOGITS
    lya
    0.16
    emez
    0.15
    iller
    0.15
     Katz
    0.15
    lush
    0.15
    _tc
    0.14
     Gram
    0.14
    翼
    0.14
    /widgets
    0.14
    linger
    0.14
    Act Density 0.122%

    No Known Activations