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

    Neuronpedia

    INDEX
    Explanations

    the mention of names, specifically first or last names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.22
    и
    -0.21
    ÛĮ
    -0.18
    ing
    -0.17
    iens
    -0.17
    iem
    -0.17
     vap
    -0.17
    aes
    -0.17
    cname
    -0.16
    iÄĻ
    -0.16
    POSITIVE LOGITS
    itionally
    0.21
    dest
    0.20
    missible
    0.19
    pole
    0.19
    ron
    0.19
    venture
    0.18
    uate
    0.18
    ulent
    0.17
    elf
    0.17
    de
    0.16
    Act Density 0.082%

    No Known Activations