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

    Neuronpedia

    INDEX
    Explanations

    references to newness or recent developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    627
    -0.15
    dea
    -0.15
     Broad
    -0.15
     strikes
    -0.14
    809
    -0.14
    506
    -0.14
    strike
    -0.14
    kara
    -0.14
    ansa
    -0.14
     Strike
    -0.14
    POSITIVE LOGITS
    ãģ°ãģĭãĤĬ
    0.25
     new
    0.20
    æĸ°çļĦ
    0.20
    à¹ĥหม
    0.18
    -new
    0.18
     newest
    0.18
     mỼi
    0.17
     nuevos
    0.17
     baru
    0.17
    new
    0.17
    Act Density 0.113%

    No Known Activations