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

    Neuronpedia

    INDEX
    Explanations

    template syntax indicators used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ières
    -0.16
    stad
    -0.15
    unden
    -0.15
    THR
    -0.15
    .volley
    -0.14
    ặn
    -0.14
    kul
    -0.14
     fitting
    -0.14
    ron
    -0.14
    omon
    -0.14
    POSITIVE LOGITS
    물
    0.15
    ött
    0.15
    \xff
    0.14
    ustum
    0.14
    HTTPHeader
    0.14
    iones
    0.14
     Huff
    0.14
    //**↵
    0.14
    edes
    0.14
     Kup
    0.14
    Act Density 0.003%

    No Known Activations