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

    Neuronpedia

    INDEX
    Explanations

    information related to software updates and version releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.69
     متعلقه
    -0.63
     myſelf
    -0.60
     right
    -0.58
     Monfieur
    -0.58
    IntoConstraints
    -0.57
     themſelves
    -0.56
    richTextPanel
    -0.56
     way
    -0.56
     people
    -0.55
    POSITIVE LOGITS
     Thereafter
    0.61
    翌日
    0.60
    期间
    0.59
    期間
    0.59
     Afterwards
    0.59
    一周
    0.59
     Afterward
    0.57
    三天
    0.57
    第二天
    0.56
    第一天
    0.55
    Act Density 0.036%

    No Known Activations