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

    Neuronpedia

    INDEX
    Explanations

    instances of the <bos> and <end> tokens within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.84
     otomatig
    -0.82
    HostException
    -0.75
    Geplaatst
    -0.73
     Paglinawan
    -0.73
     ویکی‌پدیا
    -0.73
     autorytatywna
    -0.72
    msgTypes
    -0.70
    Vidite
    -0.70
     发表于
    -0.67
    POSITIVE LOGITS
     roma
    0.54
     poffible
    0.45
     duradero
    0.43
    digen
    0.41
     negó
    0.40
     Romani
    0.40
     pleaſure
    0.39
    entuh
    0.39
    stacles
    0.38
     romana
    0.38
    Act Density 0.078%

    No Known Activations