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

    Neuronpedia

    INDEX
    Explanations

    references to layers in a structural or hierarchical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /**
    -0.88
    MemoryWarning
    -0.87
    DotNetBar
    -0.84
     MHD
    -0.84
    hlí
    -0.83
     maș
    -0.83
    )_/¯
    -0.82
     weevil
    -0.82
     تانيه
    -0.81
     riconoscimento
    -0.79
    POSITIVE LOGITS
     layers
    1.82
     Layer
    1.81
     Layers
    1.80
     layer
    1.77
     LAYER
    1.69
    Layers
    1.67
    layer
    1.64
    Layer
    1.64
    layers
    1.54
    LAYER
    1.48
    Act Density 0.065%

    No Known Activations