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

    Neuronpedia

    INDEX
    Explanations

    instances of annotations and comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.44
     pass
    -0.39
     Wow
    -0.35
     Bare
    -0.35
     labor
    -0.33
     Pass
    -0.32
    istream
    -0.32
     bare
    -0.31
     Live
    -0.31
     caught
    -0.31
    POSITIVE LOGITS
    featureID
    0.79
    MLLoader
    0.63
    存于互联网档案馆
    0.63
    since
    0.61
    disposing
    0.56
    лтемелер
    0.56
    0.55
    SourceChecksum
    0.55
    RegressionTest
    0.54
    yntaxException
    0.54
    Act Density 0.169%

    No Known Activations