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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the "<bos>" token, indicating the beginning of sections or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.88
     سكانية
    -0.87
     ddelweddau
    -0.81
    SourceChecksum
    -0.78
     समीक्षाओं
    -0.78
     nonUne
    -0.77
    AccessorTable
    -0.76
    CppCodeGen
    -0.74
    StructEnd
    -0.72
     насељу
    -0.70
    POSITIVE LOGITS
    mvn
    0.59
     StatefulWidget
    0.52
     daya
    0.47
     getNext
    0.45
    事です
    0.45
    مراجع
    0.44
     vig
    0.43
    abá
    0.43
    üyük
    0.42
    żesz
    0.41
    Act Density 0.016%

    No Known Activations