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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reau
    -0.17
    idUser
    -0.15
    rought
    -0.15
     Soon
    -0.15
    issing
    -0.14
     soon
    -0.14
    OfType
    -0.14
     Sears
    -0.14
     shr
    -0.14
    compression
    -0.14
    POSITIVE LOGITS
    ouve
    0.14
    ansi
    0.14
    readcr
    0.14
    enger
    0.14
    æł·åŃIJ
    0.14
    ichten
    0.14
    UPER
    0.14
    .ErrorCode
    0.14
    HEME
    0.13
    Ïģθ
    0.13
    Act Density 0.032%

    No Known Activations