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

    Neuronpedia

    INDEX
    Explanations

    categories and characteristics related to films and scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.95
     myſelf
    -0.94
     unſ
    -0.93
     дописавши
    -0.92
     pleaſure
    -0.92
     deſt
    -0.91
     poffible
    -0.88
     houſe
    -0.88
    ſelf
    -0.87
     itſelf
    -0.86
    POSITIVE LOGITS
    MLLoader
    0.57
    ModelSerializer
    0.54
     or
    0.47
     cons
    0.47
     &___
    0.46
     ETF
    0.44
     “
    0.43
     utama
    0.41
     
    0.41
     geçi
    0.41
    Act Density 1.074%

    No Known Activations