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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ={({
    -0.53
    orology
    -0.47
     recul
    -0.47
    atigable
    -0.45
     faits
    -0.45
    atisk
    -0.44
    Пусть
    -0.43
    ţin
    -0.43
    حس
    -0.43
    bulaire
    -0.42
    POSITIVE LOGITS
     للاسماء
    1.02
    WebpackPlugin
    0.70
    Obrázky
    0.70
    Биография
    0.68
     كومونز
    0.65
    rungsseite
    0.65
    multicolumn
    0.65
    onOptions
    0.64
     estekak
    0.64
    ⓧ
    0.63
    Act Density 2.865%

    No Known Activations