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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprising or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SEDS
    -0.50
     beginnetje
    -0.50
    ⓧ
    -0.50
    XmlAccessType
    -0.49
    WithIOException
    -0.48
     Wikimedijinoj
    -0.47
    msgTypes
    -0.46
    RegressionTest
    -0.46
    deca
    -0.46
     Destroyer
    -0.46
    POSITIVE LOGITS
     Apparently
    0.71
    Apparently
    0.71
     apparently
    0.66
     Ternyata
    0.65
    apparently
    0.58
     ternyata
    0.56
     оказалось
    0.50
     okaza
    0.49
     blijkt
    0.48
    どうやら
    0.47
    Act Density 0.285%

    No Known Activations