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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic citations

    oai_token-act-pair · gpt-3.5-turbo

    references to various statistics or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.82
    hent
    -0.68
    uca
    -0.65
    lie
    -0.65
     Rog
    -0.63
    apon
    -0.61
    iculture
    -0.61
    lio
    -0.60
     XIII
    -0.60
    atis
    -0.60
    POSITIVE LOGITS
    ³³³
    0.92
    ³³³³³³³³
    0.91
    ³³³³³³³³³³³³³³³³
    0.88
    ³³
    0.86
    ³³³³
    0.86
    è¦ļéĨĴ
    0.67
    Filename
    0.64
    Synopsis
    0.64
    dayName
    0.64
    cedented
    0.64
    Act Density 0.235%

    No Known Activations