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

    Neuronpedia

    INDEX
    Explanations

    references to administrative divisions and regional classifications in China

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    consin
    -0.46
     sûr
    -0.44
     occhiali
    -0.44
    ~
    -0.43
    loroethene
    -0.43
    المكان
    -0.43
     têtes
    -0.42
    dafri
    -0.42
     agujeros
    -0.41
     кем
    -0.41
    POSITIVE LOGITS
     AttributeSet
    0.83
    ibatis
    0.78
     itſelf
    0.77
     Theſe
    0.75
     themſelves
    0.74
    tagext
    0.72
     myſelf
    0.72
     iſt
    0.69
    ✨:
    0.69
     ſever
    0.69
    Act Density 0.416%

    No Known Activations