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

    Neuronpedia

    INDEX
    Explanations

    references to sources or citations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.55
     pleaſure
    -0.52
     Theſe
    -0.51
     Vergangenheit
    -0.49
     fileSize
    -0.49
     irland
    -0.49
     intelek
    -0.48
     säll
    -0.47
     argint
    -0.47
    Œuvres
    -0.46
    POSITIVE LOGITS
    según
    0.78
     según
    0.77
     Según
    0.77
    Según
    0.77
     לפי
    0.76
    Secondo
    0.71
     Secondo
    0.69
    Архівовано
    0.65
    rivit
    0.65
     menurut
    0.65
    Act Density 0.095%

    No Known Activations