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

    Neuronpedia

    INDEX
    Explanations

    statements about conditional relationships and causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.60
    󠁢
    -0.59
     useContext
    -0.57
    aarrggbb
    -0.55
    Ừ
    -0.53
    tainable
    -0.53
    ageable
    -0.51
     cá
    -0.51
    етра
    -0.51
    ampton
    -0.51
    POSITIVE LOGITS
     beginnetje
    0.59
    XmlAccessType
    0.59
    Geplaatst
    0.57
     ویکی‌پدیا
    0.55
    expandindo
    0.55
     étoit
    0.54
    ">//
    0.54
    KURZBESCHREIBUNG
    0.53
    Havolalar
    0.52
    paramref
    0.52
    Act Density 0.766%

    No Known Activations