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

    Neuronpedia

    INDEX
    Explanations

    start and end markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kloped
    -0.60
     Jorg
    -0.49
     God
    -0.47
     girl
    -0.47
     within
    -0.47
    Encyklopedia
    -0.46
    Identyfik
    -0.46
    тей
    -0.46
     also
    -0.45
     "&
    -0.44
    POSITIVE LOGITS
    oredCriteria
    0.78
    featureID
    0.76
    IUrlHelper
    0.69
    RuleContext
    0.69
     հղումներ
    0.64
    flink
    0.64
     ligiloj
    0.63
    forKey
    0.62
     StatefulWidget
    0.62
    lustre
    0.60
    Act Density 0.159%

    No Known Activations