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

    Neuronpedia

    INDEX
    Explanations

    connections and combinations between different concepts or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aload
    -0.53
     accompanied
    -0.48
    staan
    -0.48
    지를
    -0.48
    dataclass
    -0.48
    setHeader
    -0.47
    etCode
    -0.46
    Impl
    -0.46
    uchos
    -0.45
    BlockPos
    -0.45
    POSITIVE LOGITS
     disparate
    1.11
     elements
    0.91
     together
    0.85
    Personendaten
    0.78
     threads
    0.73
     dots
    0.71
    elements
    0.71
     mergeFrom
    0.70
     Elemente
    0.69
    enumii
    0.69
    Act Density 0.461%

    No Known Activations