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

    Neuronpedia

    INDEX
    Explanations

    instances of quotes or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /or
    -0.21
    aviest
    -0.15
    /her
    -0.15
    ht
    -0.15
    hta
    -0.15
    aps
    -0.15
    avin
    -0.14
    SEMB
    -0.14
    ki
    -0.14
    ÑģÑĤа
    -0.14
    POSITIVE LOGITS
    gth
    0.19
    itionally
    0.14
    itori
    0.14
    ubu
    0.14
    ãģĦ
    0.14
    821
    0.13
    iente
    0.13
    áci
    0.13
     Mund
    0.13
    acÃŃ
    0.13
    Act Density 0.088%

    No Known Activations