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

    Neuronpedia

    INDEX
    Explanations

    distinct structural elements or markers in written language, such as code or formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emble
    -0.49
     cordes
    -0.47
    springframework
    -0.46
    метров
    -0.46
     BioLib
    -0.45
    Ạ
    -0.45
     appunto
    -0.45
    assador
    -0.45
    élie
    -0.43
     sisi
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.96
     <=",
    0.92
    Autoritní
    0.90
     дописавши
    0.90
     الحره
    0.87
    HostException
    0.84
    OGND
    0.84
    __':
    0.79
    Geplaatst
    0.79
    uxxxx
    0.78
    Act Density 0.394%

    No Known Activations