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

    Neuronpedia

    INDEX
    Explanations

    phrases related to increases or surges in various metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    漫
    -0.16
    ãĤ¤ãĤº
    -0.14
    esi
    -0.14
    ıyla
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
    zin
    -0.14
     geç
    -0.14
    ειÏĤ
    -0.14
    åĪ¥
    -0.14
     unl
    -0.13
    POSITIVE LOGITS
     number
    0.19
     overall
    0.18
    nock
    0.17
    //{{
    0.15
    overall
    0.14
    lichkeit
    0.14
     sá»ij
    0.14
    ãĥ¯ãĥ¼
    0.14
     fewer
    0.13
     activity
    0.13
    Act Density 0.167%

    No Known Activations