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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies, citations, and data sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.84
     myſelf
    -0.82
    aarrggbb
    -0.78
     propOrder
    -0.77
     للاسماء
    -0.75
     purpoſe
    -0.73
     raiſ
    -0.72
    ſelves
    -0.72
     reaſon
    -0.71
     ſte
    -0.71
    POSITIVE LOGITS
     ,
    0.71
     ),
    0.62
     arşivlendi
    0.59
    gæ
    0.55
    存于互联网档案馆
    0.55
     ;
    0.55
     ).
    0.52
    >,
    0.52
    ),
    0.51
     (
    0.51
    Act Density 2.139%

    No Known Activations