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

    Neuronpedia

    INDEX
    Explanations

    symbols or variables used in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Wikispecies
    -0.67
    </caption>
    -0.66
     preocupes
    -0.66
     Vikipedi
    -0.64
    BeginInit
    -0.59
    labelledby
    -0.59
    олові
    -0.59
     AssemblyProduct
    -0.59
     fallu
    -0.59
    %";
    -0.59
    POSITIVE LOGITS
     disambiguazione
    0.59
    adaptiveStyles
    0.56
    esistenza
    0.53
    defineProperty
    0.51
    /***/
    0.49
    というもの
    0.47
    dAtA
    0.43
    reis
    0.41
     berta
    0.41
     ujednoznacz
    0.41
    Act Density 0.010%

    No Known Activations