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

    Neuronpedia

    INDEX
    Explanations

    configurations and compatibility settings in code or data structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.94
    =$?
    -0.88
     myſelf
    -0.87
     Efq
    -0.85
     Monfieur
    -0.85
     deſt
    -0.84
     becauſe
    -0.82
    rrggbb
    -0.82
     uſed
    -0.81
     $_"
    -0.81
    POSITIVE LOGITS
    …
    0.53
    styleable
    0.49
    emény
    0.44
     …
    0.43
    PyTuple
    0.42
    asa
    0.42
     BeautifulSoup
    0.42
    皇子
    0.41
    culin
    0.39
    ೂ
    0.39
    Act Density 0.004%

    No Known Activations