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

    Neuronpedia

    INDEX
    Explanations

    references to authority and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndInit
    -0.60
    WriteTagHelper
    -0.58
    IGraphics
    -0.54
    toMatchSnapshot
    -0.49
     consigned
    -0.48
    Pardon
    -0.48
    úgó
    -0.48
    Karla
    -0.47
     ingenu
    -0.47
    BagLayout
    -0.46
    POSITIVE LOGITS
    AutoScaleMode
    0.41
     snippetHide
    0.37
    AnchorStyles
    0.36
    Vidite
    0.34
    ChildIndex
    0.34
    %?
    0.32
     ModelExpression
    0.32
    UnifiedTopology
    0.31
     tartalomajánló
    0.31
    Données
    0.31
    Act Density 0.089%

    No Known Activations