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

    Neuronpedia

    INDEX
    Explanations

    occurrences of various forms of loss in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _OM
    -0.15
    639
    -0.14
    DRV
    -0.14
    idth
    -0.14
    569
    -0.14
    ãģĵãģĿ
    -0.14
    ignon
    -0.14
    _simps
    -0.13
    939
    -0.13
     ذات
    -0.13
    POSITIVE LOGITS
    ugu
    0.15
    /extensions
    0.14
    olor
    0.14
    avec
    0.13
    rypt
    0.13
    beck
    0.13
    íħĮ
    0.13
     имÑĥ
    0.13
    ël
    0.13
     Minh
    0.13
    Act Density 0.023%

    No Known Activations