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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "any" or related phrases indicating inclusivity or lack of restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zas
    -0.15
    rej
    -0.15
    anzi
    -0.14
    ÑĤал
    -0.14
    tems
    -0.14
    @student
    -0.13
    inati
    -0.13
    ARIO
    -0.13
    TRL
    -0.13
    asio
    -0.13
    POSITIVE LOGITS
    .trip
    0.17
    place
    0.15
     further
    0.14
    MethodImpl
    0.14
    zzle
    0.14
    ÙĪÙĨا
    0.14
    iola
    0.14
    ertz
    0.14
    doch
    0.14
    ua
    0.14
    Act Density 0.065%

    No Known Activations