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

    Neuronpedia

    INDEX
    Explanations

    elements related to comparisons and contrasts between different subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     @"/
    -0.46
    brigens
    -0.45
    RTLD
    -0.44
    czegó
    -0.41
    complexContent
    -0.41
     ModelExpression
    -0.40
    anskje
    -0.40
    ScopeManager
    -0.40
    TypedDataSet
    -0.39
    LayoutPanel
    -0.39
    POSITIVE LOGITS
     normal
    3.16
     ordinary
    2.80
    normal
    2.72
     обы
    2.59
     normale
    2.53
     normalen
    2.50
     usual
    2.44
     regular
    2.44
     normales
    2.42
    Normal
    2.39
    Act Density 2.534%

    No Known Activations