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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "of" and phrases that indicate possession or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Silent
    -0.16
    vap
    -0.15
    ritz
    -0.15
     Specialty
    -0.14
    yna
    -0.14
     cruelty
    -0.14
    ê¸Ī
    -0.14
    ÙİØŃ
    -0.14
    ureau
    -0.14
    ingers
    -0.13
    POSITIVE LOGITS
    agher
    0.17
     cand
    0.16
    ature
    0.15
    257
    0.15
    ominator
    0.14
    ë¡Ģ
    0.14
    ackson
    0.14
    ellen
    0.14
    ancial
    0.14
    ardin
    0.14
    Act Density 0.026%

    No Known Activations