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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foon
    -0.17
    iyat
    -0.16
    رÙĩ
    -0.16
    볬
    -0.15
    ÏĦοκ
    -0.14
    atk
    -0.14
    eya
    -0.14
    交
    -0.14
    avax
    -0.14
    interop
    -0.14
    POSITIVE LOGITS
    кав
    0.15
    loff
    0.14
    Ñĥз
    0.14
     Kv
    0.14
    á»ĥn
    0.14
    ç´
    0.14
    ombre
    0.13
    ajo
    0.13
    .lesson
    0.13
    orry
    0.13
    Act Density 0.159%

    No Known Activations