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

    Neuronpedia

    INDEX
    Explanations

    references to clothing and play products for children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aliz
    -0.19
    indow
    -0.18
    udur
    -0.18
    urette
    -0.17
    bic
    -0.17
    ampo
    -0.17
    abled
    -0.16
    ÄĽÅĻ
    -0.15
    agger
    -0.14
    apsed
    -0.14
    POSITIVE LOGITS
    adiens
    0.17
    gesi
    0.15
    YL
    0.15
    umar
    0.15
     User
    0.15
     ÙģÙĪت
    0.14
     disen
    0.14
    thers
    0.14
    lac
    0.13
    2
    0.13
    Act Density 0.032%

    No Known Activations