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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of centrality or focus in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĭľ
    -0.16
    .twig
    -0.15
    ãĢģãģª
    -0.15
    ãĢĤãĢĤ↵↵
    -0.14
     tele
    -0.14
    ena
    -0.14
    OGLE
    -0.14
    ella
    -0.14
     ден
    -0.13
    ÄĽle
    -0.13
    POSITIVE LOGITS
     Essence
    0.15
     guilt
    0.15
     sow
    0.15
    sz
    0.14
    ilver
    0.14
    оваÑħ
    0.14
     feeder
    0.14
    ools
    0.14
     vad
    0.14
    intage
    0.13
    Act Density 0.005%

    No Known Activations