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

    Neuronpedia

    INDEX
    Explanations

    references to cultural identity and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekil
    -0.17
    iland
    -0.16
    ritz
    -0.15
    erland
    -0.15
    resas
    -0.15
    quette
    -0.14
    alion
    -0.14
     BoxFit
    -0.14
    itecture
    -0.14
    oload
    -0.14
    POSITIVE LOGITS
    çĵľ
    0.15
     blister
    0.14
    les
    0.14
    557
    0.14
    attr
    0.14
    vla
    0.14
    294
    0.14
    unning
    0.14
    ass
    0.14
     Thur
    0.13
    Act Density 0.325%

    No Known Activations