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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between different elements or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     konserv
    -0.69
     kosme
    -0.68
     praktik
    -0.66
     Souha
    -0.62
     Belén
    -0.61
     notor
    -0.59
     Darío
    -0.59
     Mónica
    -0.59
     Haci
    -0.58
     afront
    -0.58
    POSITIVE LOGITS
     connections
    0.95
     linkages
    0.82
     linking
    0.81
     connecting
    0.80
     interconnected
    0.79
     interconnection
    0.78
    connections
    0.78
     Connections
    0.75
     connectors
    0.74
     links
    0.74
    Act Density 0.606%

    No Known Activations