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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and structures related to graphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äl
    -0.16
    ½æķ°
    -0.16
    usat
    -0.15
     bump
    -0.15
    ensch
    -0.15
     mars
    -0.14
    endencies
    -0.14
    Įĵ
    -0.14
     Nun
    -0.14
     spot
    -0.13
    POSITIVE LOGITS
     graphs
    0.45
     graph
    0.44
     Graph
    0.37
    graphs
    0.36
    graph
    0.36
    Graph
    0.35
    _graph
    0.34
    -graph
    0.34
    .graph
    0.33
    agraph
    0.32
    Act Density 0.175%

    No Known Activations