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

    Neuronpedia

    INDEX
    Explanations

    phrases and reflections on timing and memory

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ✨:
    -0.64
    MLLoader
    -0.64
    Erreferentziak
    -0.57
     onCancelled
    -0.57
     moments
    -0.56
     gql
    -0.56
    innig
    -0.56
    KELEY
    -0.54
     periods
    -0.54
    couvrez
    -0.54
    POSITIVE LOGITS
    maß
    0.59
    Already
    0.59
     AssemblyVersion
    0.58
     already
    0.57
     ujednoznacz
    0.57
     ALREADY
    0.57
    ്ട
    0.57
     Already
    0.57
    testens
    0.57
     metade
    0.56
    Act Density 0.009%

    No Known Activations