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

    Neuronpedia

    INDEX
    Explanations

    commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     f
    -0.17
    lace
    -0.15
    hip
    -0.15
    fact
    -0.14
    iaz
    -0.14
    ¨
    -0.14
    hist
    -0.14
    å¤ķ
    -0.14
    oir
    -0.14
     Lace
    -0.13
    POSITIVE LOGITS
    upp
    0.16
     pás
    0.15
    ancel
    0.15
    Marshal
    0.14
    -dismiss
    0.14
    SelfPermission
    0.14
    анÑģи
    0.14
    velt
    0.14
    bane
    0.14
    inç
    0.14
    Act Density 0.009%

    No Known Activations