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

    Neuronpedia

    INDEX
    Explanations

    programming-related questions and references to code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /sweetalert
    -0.14
    itive
    -0.14
     ÙħعÙĦ
    -0.14
    uthor
    -0.14
    Fal
    -0.14
    wers
    -0.14
     lagi
    -0.14
    ARDS
    -0.13
    ards
    -0.13
    oubles
    -0.13
    POSITIVE LOGITS
     something
    0.75
    something
    0.66
     Something
    0.63
    Something
    0.61
    omething
    0.49
     iets
    0.40
     algo
    0.35
     like
    0.34
     nÄĽco
    0.34
     etwas
    0.32
    Act Density 0.107%

    No Known Activations