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

    Neuronpedia

    INDEX
    Explanations

    possessive forms and cultural references related to personal identity or heritage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.20
    \grid
    -0.15
    ksi
    -0.15
    Ãłm
    -0.14
    vana
    -0.14
    enate
    -0.14
    estruct
    -0.14
    quam
    -0.14
    ENCIL
    -0.14
    (es
    -0.14
    POSITIVE LOGITS
     themselves
    0.27
    们
    0.26
     thems
    0.19
    ths
    0.18
     koje
    0.17
    åĢij
    0.16
    eti
    0.15
     meisten
    0.15
    ibur
    0.15
    ÑĨа
    0.14
    Act Density 0.170%

    No Known Activations