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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authorship, approval, and collaboration in research documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ComponentModel
    -0.48
    zate
    -0.41
     phúc
    -0.40
    lexikon
    -0.40
    ˈ
    -0.40
    URIComponent
    -0.39
     recommandée
    -0.39
     solid
    -0.38
     tek
    -0.38
    نظر
    -0.38
    POSITIVE LOGITS
    1.42
    tvguidetime
    1.38
    NameInMap
    1.32
     مشين
    1.31
    rungsseite
    1.30
    abestanden
    1.26
     autorytatywna
    1.26
    expandindo
    1.24
     ویکی‌پدی
    1.22
     okuyayım
    1.15
    Act Density 0.492%

    No Known Activations