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

    Neuronpedia

    INDEX
    Explanations

    references to specific mathematical corollaries

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     PFA
    -0.80
     SRA
    -0.79
    bestos
    -0.79
     Wigan
    -0.79
     Anchorage
    -0.79
     scorso
    -0.79
     OBO
    -0.79
     Sra
    -0.78
     Duluth
    -0.78
     ModelExpression
    -0.77
    POSITIVE LOGITS
    Corollary
    1.39
     Corollary
    1.16
    corollary
    0.84
     corollary
    0.62
     co
    0.61
     Cor
    0.60
     Co
    0.60
    t
    0.57
     AssemblyCompany
    0.56
    gios
    0.52
    Act Density 0.004%

    No Known Activations