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

    Neuronpedia

    INDEX
    Explanations

    conjunctive phrases that express relationships or connections between multiple elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teis
    -0.69
    PagerAdapter
    -0.62
     jellemző
    -0.61
     coper
    -0.59
     Rie
    -0.58
    Vien
    -0.57
     mData
    -0.56
     áng
    -0.55
    得到了
    -0.55
    WhereInput
    -0.55
    POSITIVE LOGITS
     make
    0.92
     help
    0.89
     build
    0.84
    PerformLayout
    0.84
     create
    0.83
     take
    0.81
     Pennington
    0.81
     uſe
    0.81
     myſelf
    0.80
     meet
    0.79
    Act Density 0.275%

    No Known Activations