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

    Neuronpedia

    INDEX
    Explanations

    special characters or specific formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.91
    BibitemShut
    -0.89
    TagMode
    -0.88
     kaarangay
    -0.87
     vectorielle
    -0.86
     queſta
    -0.84
    actéristi
    -0.82
     المعيارى
    -0.81
    chieht
    -0.80
     Keuangan
    -0.79
    POSITIVE LOGITS
     bir
    0.42
     tak
    0.41
     ek
    0.40
    ],
    0.39
     ),
    0.39
     kon
    0.38
     bu
    0.38
     bil
    0.37
    老
    0.36
     kanad
    0.35
    Act Density 0.023%

    No Known Activations