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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yt
    -0.17
    omo
    -0.16
    zet
    -0.15
     inst
    -0.15
     SID
    -0.15
    ÏĢη
    -0.15
     Larson
    -0.14
    éŁ
    -0.14
    trap
    -0.14
    opia
    -0.14
    POSITIVE LOGITS
    ason
    0.15
    aks
    0.15
    ottle
    0.15
    æ£ĭ
    0.14
    gens
    0.14
    ños
    0.13
    /Foundation
    0.13
     latter
    0.13
    nÃŃky
    0.13
    720
    0.13
    Act Density 0.325%

    No Known Activations