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

    Neuronpedia

    INDEX
    Explanations

    structural and syntactical elements in code-like documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.64
    esez
    -0.52
    ».
    -0.52
    SharedDtor
    -0.48
     laude
    -0.46
     ويكيميديا
    -0.45
    czegóły
    -0.43
    Shaders
    -0.43
     juridiques
    -0.42
     legales
    -0.42
    POSITIVE LOGITS
    исленность
    0.81
    __(/*!
    0.72
    WithMany
    0.66
     contextLoads
    0.65
    SourceChecksum
    0.65
    τως
    0.64
    ]--;
    0.62
     difference
    0.61
     queſta
    0.61
    zeciw
    0.61
    Act Density 0.589%

    No Known Activations