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

    Neuronpedia

    INDEX
    Explanations

    instances of the opening token '<bos>'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.81
    IUrlHelper
    -0.78
    ########.
    -0.76
     المعيارى
    -0.74
    مصادر
    -0.73
    extAlignment
    -0.68
     lenker
    -0.65
    Personensuche
    -0.64
     صوتيه
    -0.64
    \{\\
    -0.64
    POSITIVE LOGITS
    랙
    0.53
    Davis
    0.50
    ())))
    0.50
     Davis
    0.49
    pas
    0.49
    下载附件
    0.48
    itaria
    0.48
    HasBeenSet
    0.48
    sproble
    0.47
    ga
    0.46
    Act Density 0.253%

    No Known Activations