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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and elements related to research studies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    üğ
    -0.42
     Cap
    -0.41
    Cap
    -0.41
    rungs
    -0.40
     cele
    -0.40
    pendi
    -0.39
    Care
    -0.39
     inmedi
    -0.38
     cap
    -0.38
    ರೆ
    -0.38
    POSITIVE LOGITS
    تقاوى
    0.75
     contextLoads
    0.74
     للمعارف
    0.73
     Houſe
    0.73
    Sklici
    0.73
    hastly
    0.73
     Cæsar
    0.72
     kasarigan
    0.71
    TagMode
    0.70
    PyExc
    0.70
    Act Density 0.364%

    No Known Activations