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

    Neuronpedia

    INDEX
    Explanations

    terminology related to graph theory and edges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     */
    -0.88
     >=",
    -0.84
    romyal
    -0.82
    rawdę
    -0.82
    างเกง
    -0.82
     pitié
    -0.81
     costumi
    -0.80
    >*/
    -0.80
    érables
    -0.77
    gameserver
    -0.77
    POSITIVE LOGITS
     Edge
    2.26
     edge
    2.12
     EDGE
    2.10
    Edge
    2.06
     edges
    1.98
    edge
    1.90
    EDGE
    1.89
     Edges
    1.79
    Edges
    1.72
    edges
    1.63
    Act Density 0.046%

    No Known Activations