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

    Neuronpedia

    INDEX
    Explanations

    words indicating significant importance or prominence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ych
    -0.17
    inator
    -0.16
    odb
    -0.15
    iggins
    -0.14
    fulness
    -0.14
    ijkstra
    -0.14
    ett
    -0.14
    obox
    -0.14
    enberg
    -0.14
    BASE
    -0.14
    POSITIVE LOGITS
    -league
    0.28
    /min
    0.21
    ardi
    0.18
    /main
    0.18
    league
    0.17
     league
    0.17
    itarian
    0.16
    eru
    0.15
     League
    0.14
    ãĥ£
    0.14
    Act Density 0.023%

    No Known Activations