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

    Neuronpedia

    INDEX
    Explanations

    references to external links or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.15
    hv
    -0.14
     embr
    -0.14
    immer
    -0.14
     I
    -0.14
    /
    -0.14
    rowse
    -0.14
     fire
    -0.14
     Ã
    -0.14
     English
    -0.14
    POSITIVE LOGITS
    AdapterFactory
    0.17
    atten
    0.16
    jedn
    0.16
    æĪ¸
    0.16
    inspace
    0.15
    etta
    0.15
    okrat
    0.15
    ÑĤÑİ
    0.15
    ILON
    0.15
    phans
    0.15
    Act Density 0.001%

    No Known Activations