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

    Neuronpedia

    INDEX
    Explanations

    negation or expressions indicating exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sør
    -0.54
     act
    -0.53
     idéia
    -0.52
     egli
    -0.51
    zlich
    -0.50
     Поли
    -0.50
     pontu
    -0.50
     G
    -0.50
    da
    -0.50
    Act
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    1.03
     AssemblyVersion
    1.02
     autorytatywna
    0.93
    NameInMap
    0.92
    ConstraintMaker
    0.91
    GraphicsUnit
    0.89
    IntoConstraints
    0.88
    tangentMode
    0.85
    PerformLayout
    0.85
     Réponses
    0.83
    Act Density 0.070%

    No Known Activations