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

    Neuronpedia

    INDEX
    Explanations

    references to global variables and objects in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vyk
    -0.15
    roje
    -0.15
    ivant
    -0.15
    _WM
    -0.14
    룸
    -0.14
    PED
    -0.14
    лиÑı
    -0.14
    ******/
    -0.14
     batching
    -0.13
    yonel
    -0.13
    POSITIVE LOGITS
    ika
    0.18
     compared
    0.16
     Fee
    0.14
    Finder
    0.14
     pom
    0.14
     Chan
    0.14
    tron
    0.14
     Randolph
    0.14
     s
    0.14
    anda
    0.14
    Act Density 0.019%

    No Known Activations