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

    Neuronpedia

    INDEX
    Explanations

    references to transcripts or transcript-related content

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.98
     שוליים
    -0.85
    ?>">
    -0.85
     "..\..\..\
    -0.84
    Kjelder
    -0.82
    BufferException
    -0.82
    ViewFeatures
    -0.81
    >")
    -0.81
    "}>
    -0.81
     @"/
    -0.80
    POSITIVE LOGITS
     transcripts
    1.04
     Transcript
    1.03
     transcript
    1.03
    transcript
    0.91
    Transcript
    0.90
    cripts
    0.68
     appelez
    0.62
    Calla
    0.61
    SCRIPT
    0.60
     GUST
    0.60
    Act Density 0.004%

    No Known Activations