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

    Neuronpedia

    INDEX
    Explanations

    patterns related to dependency and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Xem
    -0.16
    ted
    -0.15
    eden
    -0.15
    enburg
    -0.15
     gradually
    -0.14
    _sqrt
    -0.14
    æ¸Ī
    -0.14
    ened
    -0.14
    catch
    -0.14
    cur
    -0.13
    POSITIVE LOGITS
    ocê
    0.16
    Leaks
    0.15
    659
    0.14
    Łèĥ½
    0.14
     Grat
    0.14
    аÑģÑĤи
    0.14
    à¸ķาม
    0.14
    icom
    0.14
    emy
    0.13
    mx
    0.13
    Act Density 0.059%

    No Known Activations