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

    Neuronpedia

    INDEX
    Explanations

    file directory and component identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     invokingState
    -0.84
    новниш
    -0.70
     المعيارى
    -0.68
    الإنجليزية
    -0.66
    CppCodeGen
    -0.66
    fitrión
    -0.65
    NameInMap
    -0.65
     OMITBAD
    -0.65
     وتسجيلات
    -0.62
     الحره
    -0.61
    POSITIVE LOGITS
    enumi
    0.46
    MI
    0.45
    v
    0.44
    خصة
    0.44
     elefante
    0.44
     ...
    0.43
    MessageTagHelper
    0.43
    ود
    0.43
     vulgares
    0.43
    TagMode
    0.42
    Act Density 1.393%

    No Known Activations