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

    Neuronpedia

    INDEX
    Explanations

    words that demonstrate complexity or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wise
    -0.17
    rier
    -0.16
    gett
    -0.15
    icot
    -0.14
    platz
    -0.14
    âĺħ
    -0.14
     Morse
    -0.14
     æĪ
    -0.14
    de
    -0.13
    riage
    -0.13
    POSITIVE LOGITS
    odem
    0.20
    Uvs
    0.17
    áš
    0.16
    Ïĥκε
    0.15
    anza
    0.14
    Ø´ÙĨ
    0.14
     darm
    0.14
    addon
    0.14
     reluct
    0.14
     Hasan
    0.14
    Act Density 0.002%

    No Known Activations