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

    Neuronpedia

    INDEX
    Explanations

    references to symbols and their representations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     createSlice
    -0.68
    sizeCache
    -0.64
     wyś
    -0.63
    WriteAttribute
    -0.63
    RunWith
    -0.62
     Garry
    -0.61
     يتيمه
    -0.61
     HAV
    -0.61
    เภ
    -0.61
    <h5>
    -0.60
    POSITIVE LOGITS
     symbols
    1.76
     symbol
    1.65
     Symbols
    1.63
     SYMBOL
    1.61
    symbols
    1.59
    Symbols
    1.58
     Symbol
    1.57
    SYMBOL
    1.52
    symbol
    1.52
    Symbol
    1.43
    Act Density 0.092%

    No Known Activations