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

    Neuronpedia

    INDEX
    Explanations

    proper nouns that indicate people, places, or notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Evans
    -0.80
     moons
    -0.79
    väll
    -0.77
    ications
    -0.72
    şak
    -0.72
    phosa
    -0.72
    ainville
    -0.71
    Vall
    -0.71
     Durant
    -0.70
     Busch
    -0.70
    POSITIVE LOGITS
     Stö
    0.77
     Elli
    0.76
    |<\
    0.76
     Kea
    0.73
    plo
    0.73
     Merri
    0.72
     Verbre
    0.72
    WebServlet
    0.72
     Cotter
    0.71
    gio
    0.69
    Act Density 0.797%

    No Known Activations