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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming constructs and data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.93
    principalColumn
    -0.91
    parsedMessage
    -0.90
     CreateTagHelper
    -0.79
    PhysRevD
    -0.76
     GenerationType
    -0.75
    TypedDataSet
    -0.75
     Económica
    -0.73
    DoubleQuotes
    -0.71
     ModelExpression
    -0.71
    POSITIVE LOGITS
     Gew
    0.47
    必
    0.41
     Min
    0.41
    osomal
    0.40
    כי
    0.40
     ma
    0.39
    évaluateur
    0.39
    uber
    0.39
    utra
    0.39
    opt
    0.38
    Act Density 0.948%

    No Known Activations