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

    Neuronpedia

    INDEX
    Explanations

    references to edges in a graphical representation or model

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pitié
    -0.86
     disegni
    -0.83
    างเกง
    -0.82
    __*/
    -0.82
     complètes
    -0.79
    romyal
    -0.77
     sauvages
    -0.77
    >*/
    -0.76
     */
    -0.76
    uginosa
    -0.76
    POSITIVE LOGITS
     Edge
    1.73
     EDGE
    1.67
    Edge
    1.53
     edge
    1.52
     edges
    1.49
    EDGE
    1.45
    Edges
    1.36
    edge
    1.36
     Edg
    1.36
     Edges
    1.33
    Act Density 0.084%

    No Known Activations