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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "hidden" in various contexts, particularly related to layers and variables in neural networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.06
    UserScript
    -0.96
    MigrationBuilder
    -0.94
     postIndex
    -0.91
    NamedQueries
    -0.89
    setVerticalGroup
    -0.86
     dequeue
    -0.82
     caminhão
    -0.81
     SqlCommand
    -0.80
     comigo
    -0.79
    POSITIVE LOGITS
     Hidden
    1.47
     hidden
    1.40
    Hidden
    1.31
    hidden
    1.30
    HIDDEN
    1.27
    隐
    0.82
    isHidden
    0.78
     embedded
    0.77
     caché
    0.77
    隱
    0.76
    Act Density 0.115%

    No Known Activations