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

    Neuronpedia

    INDEX
    Explanations

    references to shocking or disturbing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abol
    -0.07
    ature
    -0.07
    infos
    -0.07
     Bakan
    -0.07
    umi
    -0.07
    æIJŃ
    -0.07
    лиÑĪ
    -0.06
    нин
    -0.06
    æĿŁ
    -0.06
    grant
    -0.06
    POSITIVE LOGITS
    ãģı
    0.07
     modal
    0.06
    anz
    0.06
    /Runtime
    0.06
    377
    0.06
    617
    0.05
     domic
    0.05
    aal
    0.05
     bas
    0.05
     McL
    0.05
    Act Density 0.001%

    No Known Activations